Update Ren(G_i) per WD-imsc-hrm-20220322

Added missing entries to codepoint sets used to compute `GCpy` and `Ren(G_i)`

scripts/make_gcpy_source.py → scripts/make_codepoint_sets.py

@@ -23,9 +23,8 @@
 # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
 # SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
-"""Generates a Python source file that initializes a set of unicode codepoints that belong 
-to the following scripts: latin, greek, cyrillic, hebrew or common.
-Used to determine the value of GCpy at IMSC, 10.5"""
+"""Generates a Python source file that contains sets of Unicode codepoints used
+by the IMSC HRM, e.g., to determine the value of GCpy at IMSC, 10.5"""
 
 __author__ = "Pierre-Anthony Lemieux <[email protected]>"
 
@@ -35,35 +34,44 @@
 TEMPLATE="""#!/usr/bin/env python
 # -*- coding: UTF-8 -*-
 
-'''Set of unicode codepoints that belong to the following scripts: latin, greek, cyrillic, hebrew or common.
-Used to determine the value of GCpy at IMSC, 10.5'''
+'''Sets of Unicode codepoints used by the IMSC HRM.'''
 
 # Generated from the Unicode Character Database (http://www.unicode.org/Public/UNIDATA/Scripts.txt)
 # Version: {version}
 # Date: {date}
 
+# Normalized glyph copy performance factor (GCpy) for Latin, Greek, Cyrillic, Hebrew or Common
 GCPY_12 = set(
 (
-{codepoints}
+{codepoints_GCPY_12}
+)
+)
+
+# Text rendering performance factor Ren(Gi) for Han, Katakana, Hiragana, Bopomofo or Hangul scripts
+RENGI_06 = set(
+(
+{codepoints_RENGI_06}
 )
 )
 """
 
-SCRIPT_LINE_PATTERN = re.compile(r"(?P<start>[a-fA-F0-9]{4})(?:\.\.(?P<end>[a-fA-F0-9]{4})?)\s+;\s+(?P<script>\w*)")
+SCRIPT_LINE_PATTERN = re.compile(r"(?P<start>[a-fA-F0-9]{4})(?:\.\.(?P<end>[a-fA-F0-9]{4}))?\s+;\s+(?P<script>\w*)")
 
 VERSION_LINE_PATTERN = re.compile(r"^#\s+(.+)$")
 
 DATE_LINE_PATTERN = re.compile(r"^#\s*Date:\s*(.+)$")
 
 if __name__ == '__main__':
-  parser = argparse.ArgumentParser(description='Generates the _GCPY_12.py file')
+  parser = argparse.ArgumentParser(description='Generates the _codepoints_sets.py file')
   parser.add_argument('scripts_file', type=str, help='Path to the input unicode Scripts.txt file')
-  parser.add_argument('gcpy_py_file', type=str, help='Path to the generated Python source file')
+  parser.add_argument('py_file', type=str, help='Path to the generated Python source file')
 
   args = parser.parse_args()
 
   gcpy_12 = set()
 
+  rengi_06 = set()
+
   with open(args.scripts_file, encoding="latin-1") as f:
 
     file_version = VERSION_LINE_PATTERN.match(f.readline()).group(1)
@@ -76,21 +84,28 @@
       if m is None:
         continue
 
-      if m.group("script").lower() not in ("common", "latin", "greek", "hebrew", "cyrillic"):
+      script = m.group("script").lower()
+
+      if script in ("common", "latin", "greek", "hebrew", "cyrillic"):
+        cp_group = gcpy_12
+      elif script in ("han", "katakana", "hiragana", "bopomofo", "hangul"):
+        cp_group = rengi_06
+      else:
         continue
 
       start = int(m.group("start"), 16)
 
       end = int(m.group("end"), 16) if m.group("end") is not None else start + 1
 
       for i in range(start, end):
-        gcpy_12.add(i)
+        cp_group.add(i)
 
-  with open(args.gcpy_py_file, "w", encoding="utf-8") as f:
+  with open(args.py_file, "w", encoding="utf-8") as f:
 
     f.write(
       TEMPLATE.format(
-        codepoints=",\n".join(map(str, gcpy_12)),
+        codepoints_GCPY_12=",\n".join(map(str, gcpy_12)),
+        codepoints_RENGI_06=",\n".join(map(str, rengi_06)),
         date=file_date,
         version=file_version
       )