fonts: Include in fake Arial all the codepoints from the original font.

New fonts are from https://github.com/notofonts/noto-fonts.git at
2725c70baa8b0176c7577093ba1fc6179aa79478, in the hinted/ttf folder.

Makefile.in

@@ -740,31 +740,34 @@ noto_sans.ttf = $(FONTS)/noto/NotoSans-Regular.ttf
 noto_sans_arabic.ttf = $(FONTS)/noto/NotoSansArabic-Regular.ttf
 noto_sans_armenian.ttf = $(FONTS)/noto/NotoSansArmenian-Regular.ttf
 noto_sans_bengali.ttf = $(FONTS)/noto/NotoSansBengali-Regular.ttf
+noto_sans_bengaliui.ttf = $(FONTS)/noto/NotoSansBengaliUI-Regular.ttf
 noto_sans_coptic.ttf = $(FONTS)/noto/NotoSansCoptic-Regular.ttf
+noto_sans_devanagariui.ttf = $(FONTS)/noto/NotoSansDevanagariUI-Regular.ttf
 noto_sans_georgian.ttf = $(FONTS)/noto/NotoSansGeorgian-Regular.ttf
 noto_sans_gujarati.ttf = $(FONTS)/noto/NotoSansGujarati-Regular.ttf
-noto_sans_hebrew.ttf = $(FONTS)/noto/NotoSansHebrew-Regular.ttf
-noto_sans_khmer.ttf = $(FONTS)/noto/NotoSansKhmer-Regular.ttf
-noto_sans_tamil.ttf = $(FONTS)/noto/NotoSansTamil-Regular.ttf
-noto_sans_thaana.ttf = $(FONTS)/noto/NotoSansThaana-Regular.ttf
-noto_sans_thai.ttf = $(FONTS)/noto/NotoSansThai-Regular.ttf
-micross.ttf = $(FONTS_OBJ)/micross.ttf
-
-noto_sans_bengaliui.ttf = $(FONTS)/noto/NotoSansBengaliUI-Regular.ttf
-noto_sans_devanagariui.ttf = $(FONTS)/noto/NotoSansDevanagariUI-Regular.ttf
 noto_sans_gujaratiui.ttf = $(FONTS)/noto/NotoSansGujaratiUI-Regular.ttf
 noto_sans_gurmukhiui.ttf = $(FONTS)/noto/NotoSansGurmukhiUI-Regular.ttf
+noto_sans_hebrew.ttf = $(FONTS)/noto/NotoSansHebrew-Regular.ttf
 noto_sans_kannadaui.ttf = $(FONTS)/noto/NotoSansKannadaUI-Regular.ttf
+noto_sans_khmer.ttf = $(FONTS)/noto/NotoSansKhmer-Regular.ttf
 noto_sans_malayalamui.ttf = $(FONTS)/noto/NotoSansMalayalamUI-Regular.ttf
+noto_sans_math.ttf = $(FONTS)/noto/NotoSansMath-Regular.ttf
 noto_sans_meeteimayek.ttf = $(FONTS)/noto/NotoSansMeeteiMayek-Regular.ttf
+noto_sans_mono.ttf = $(FONTS)/noto/NotoSansMono-Regular.ttf
 noto_sans_olchiki.ttf = $(FONTS)/noto/NotoSansOlChiki-Regular.ttf
 noto_sans_oriyaui.ttf = $(FONTS)/noto/NotoSansOriyaUI-Regular.ttf
 noto_sans_sinhalaui.ttf = $(FONTS)/noto/NotoSansSinhalaUI-Regular.ttf
 noto_sans_sorasompeng.ttf = $(FONTS)/noto/NotoSansSoraSompeng-Regular.ttf
+noto_sans_symbols.ttf = $(FONTS)/noto/NotoSansSymbols-Regular.ttf
+noto_sans_symbols2.ttf = $(FONTS)/noto/NotoSansSymbols2-Regular.ttf
+noto_sans_tamil.ttf = $(FONTS)/noto/NotoSansTamil-Regular.ttf
 noto_sans_tamilui.ttf = $(FONTS)/noto/NotoSansTamilUI-Regular.ttf
 noto_sans_teluguui.ttf = $(FONTS)/noto/NotoSansTeluguUI-Regular.ttf
-nirmala.ttf = $(FONTS_OBJ)/nirmala.ttf
+noto_sans_thaana.ttf = $(FONTS)/noto/NotoSansThaana-Regular.ttf
+noto_sans_thai.ttf = $(FONTS)/noto/NotoSansThai-Regular.ttf
 
+micross.ttf = $(FONTS_OBJ)/micross.ttf
+nirmala.ttf = $(FONTS_OBJ)/nirmala.ttf
 alt_arial.ttf = $(ALT_FONTS_OBJ)/arial.ttf
 
 #The use of "Arial" here is for compatibility with programs that require that exact string. This font is not Arial.
@@ -834,7 +837,7 @@ $(micross.ttf): $(FONTS)/scripts/merge.py $(noto_sans.ttf) $(noto_sans_arabic.tt
 		$(noto_sans_thaana.ttf) $(noto_sans_thai.ttf)
 	$(FONTS)/scripts/merge.py $(noto_sans.ttf) $(noto_sans_arabic.ttf) $(noto_sans_armenian.ttf) $(noto_sans_bengali.ttf) \
 		$(noto_sans_coptic.ttf) $(noto_sans_georgian.ttf) $(noto_sans_gujarati.ttf) $(noto_sans_hebrew.ttf) $(noto_sans_khmer.ttf) \
-		$(noto_sans_tamil.ttf) $(noto_sans_thaana.ttf) $(noto_sans_thai.ttf) "MicrosoftSansSerif" "Microsoft Sans Serif" "Regular" $(micross.ttf)
+		$(noto_sans_tamil.ttf) $(noto_sans_thaana.ttf) $(noto_sans_thai.ttf) "MicrosoftSansSerif" "Microsoft Sans Serif" "Regular" /dev/null $(micross.ttf)
 
 $(nirmala.ttf): $(FONTS)/scripts/merge.py $(noto_sans.ttf) $(noto_sans_bengaliui.ttf) $(noto_sans_devanagariui.ttf) $(noto_sans_gujaratiui.ttf) $(noto_sans_gurmukhiui.ttf) \
 		$(noto_sans_kannadaui.ttf) $(noto_sans_malayalamui.ttf) $(noto_sans_meeteimayek.ttf) $(noto_sans_olchiki.ttf) $(noto_sans_oriyaui.ttf) \
@@ -842,10 +845,12 @@ $(nirmala.ttf): $(FONTS)/scripts/merge.py $(noto_sans.ttf) $(noto_sans_bengaliui
 	$(FONTS)/scripts/merge.py $(noto_sans.ttf) $(noto_sans_bengaliui.ttf) $(noto_sans_devanagariui.ttf) $(noto_sans_gujaratiui.ttf) \
 		$(noto_sans_gurmukhiui.ttf) $(noto_sans_kannadaui.ttf) $(noto_sans_malayalamui.ttf) $(noto_sans_meeteimayek.ttf) $(noto_sans_olchiki.ttf) \
 		$(noto_sans_oriyaui.ttf) $(noto_sans_sinhalaui.ttf) $(noto_sans_sorasompeng.ttf) $(noto_sans_tamilui.ttf) $(noto_sans_teluguui.ttf) \
-		"NirmalaUI" "Nirmala UI" "Regular" $(nirmala.ttf)
+		"NirmalaUI" "Nirmala UI" "Regular" /dev/null $(nirmala.ttf)
 
-$(alt_arial.ttf): $(FONTS)/scripts/merge.py $(noto_sans.ttf) $(noto_sans_arabic.ttf) $(noto_sans_hebrew.ttf) | $(ALT_FONTS_OBJ)
+$(alt_arial.ttf): $(FONTS)/scripts/merge.py $(noto_sans.ttf) $(noto_sans_arabic.ttf) $(noto_sans_hebrew.ttf) $(noto_sans_armenian.ttf) $(noto_sans_coptic.ttf) \
-	$(FONTS)/scripts/merge.py $(noto_sans.ttf) $(noto_sans_arabic.ttf) $(noto_sans_hebrew.ttf) "Arial" "Arial" "Regular" $(alt_arial.ttf)
+		$(noto_sans_math.ttf) $(noto_sans_symbols.ttf) $(noto_sans_symbols2.ttf) $(noto_sans_mono.ttf) | $(ALT_FONTS_OBJ)
+	$(FONTS)/scripts/merge.py $(noto_sans.ttf) $(noto_sans_arabic.ttf) $(noto_sans_hebrew.ttf) $(noto_sans_armenian.ttf) $(noto_sans_coptic.ttf) \
+		$(noto_sans_math.ttf) $(noto_sans_symbols.ttf) $(noto_sans_symbols2.ttf) $(noto_sans_mono.ttf) "Arial" "Arial" "Regular" $(FONTS)/ranges/arial $(alt_arial.ttf)
 
 fonts: $(msyh.ttf)
 fonts: $(simsun.ttc)

fonts/ranges/arial

@@ -0,0 +1,140 @@
+0020-007E
+00A0-0377
+037A-037F
+0384-038A
+038C
+038E-03A1
+03A3-052F
+0531-0556
+0559-055F
+0561-0587
+0589-058A
+058D-058F
+0591-05C7
+05D0-05EA
+05F0-05F4
+0600-061C
+061E-06FF
+0750-077F
+08A0-08B4
+08B6-08BD
+08D4-08FF
+1D00-1DCA
+1DFE-1F15
+1F18-1F1D
+1F20-1F45
+1F48-1F4D
+1F50-1F57
+1F59
+1F5B
+1F5D
+1F5F-1F7D
+1F80-1FB4
+1FB6-1FC4
+1FC6-1FD3
+1FD6-1FDB
+1FDD-1FEF
+1FF2-1FF4
+1FF6-1FFE
+2000-200F
+2012-2022
+2026
+202A-2030
+2032-2034
+2039-203A
+203C-203E
+2044
+205E
+206A-2070
+2074-2079
+207F
+2090-2094
+20A0-20BF
+20F0
+2105
+2113
+2116-2117
+2122
+2126
+212E
+214D-214E
+2153-2154
+215B-215E
+2184
+2190-2195
+21A8
+2202
+2206
+220F
+2211-2212
+2215
+2219-221A
+221E-221F
+2229
+222B
+2248
+2260-2261
+2264-2265
+2302
+2310
+2320-2321
+2500
+2502
+250C
+2510
+2514
+2518
+251C
+2524
+252C
+2534
+253C
+2550-256C
+2580
+2584
+2588
+258C
+2590-2593
+25A0-25A1
+25AA-25AC
+25B2
+25BA
+25BC
+25C4
+25CA-25CC
+25CF
+25D8-25D9
+25E6
+263A-263C
+2640
+2642
+2660
+2663
+2665-2666
+266A-266B
+266F
+2C60-2C7F
+2E17
+A717-A7AE
+A7B0-A7B7
+A7F7-A7FF
+AB30-AB65
+FB00-FB06
+FB13-FB17
+FB1D-FB36
+FB38-FB3C
+FB3E
+FB40-FB41
+FB43-FB44
+FB46-FBC1
+FBD3-FBFF
+FC5E-FC63
+FCF2-FCF4
+FD3C-FD3F
+FDF2
+FDF4
+FDFA-FDFD
+FE20-FE23
+FE70-FE74
+FE76-FEFC
+FFFC

fonts/scripts/merge.py

@@ -1,5 +1,7 @@
 #!/usr/bin/env python3
 
+# This script was created by Giovanni Mascellani for CodeWeavers
+
 # Based on merge_noto.py and merge_fonts.py from the nototools
 # (https://github.com/googlefonts/nototools), with the following
 # copyright notice:
@@ -25,6 +27,15 @@
 # Copyright 2019 Christopher Simpkins
 # MIT License
 
+# The font subsetting logic is taken from
+# https://github.com/fonttools/fonttools/blob/main/Lib/fontTools/subset/__init__.py
+# with the following copyright notice:
+
+# Copyright 2013 Google, Inc. All Rights Reserved.
+# Google Author(s): Behdad Esfahbod
+
+# The whole fonttools repository is distributed under the MIT license.
+
 """Merges a number of Noto fonts and then sets a given name to the
 result.
 
@@ -36,6 +47,7 @@ import os
 
 from fontTools import merge
 from fontTools import ttLib
+from fontTools import subset
 from fontTools.ttLib.tables import otTables
 
 def read_line_metrics(font):
@@ -215,26 +227,54 @@ def add_gsub_to_font(fontfile):
     font.save(target_file)
     return target_file
 
+def parse_unicodes(s):
+    import re
+
+    s = re.sub(r"0[xX]", " ", s)
+    s = re.sub(r"[<+>,;&#\\xXuU\n	]", " ", s)
+    l = []
+    for item in s.split():
+        fields = item.split("-")
+        if len(fields) == 1:
+            l.append(int(item, 16))
+        else:
+            start, end = fields
+            l.extend(range(int(start, 16), int(end, 16) + 1))
+    return l
+
 def main():
     output_filename = sys.argv[-1]
-    weight = sys.argv[-2]
+    ranges_filename = sys.argv[-2]
-    font_name = sys.argv[-3]
+    weight = sys.argv[-3]
-    ps_name = sys.argv[-4]
+    font_name = sys.argv[-4]
-    input_filenames = sys.argv[1:-4]
+    ps_name = sys.argv[-5]
+    input_filenames = sys.argv[1:-5]
 
-    # Add a GSUB table to the fonts that do not have one
+    # Add a GSUB table to the fonts that do not have one, otherwise
+    # the merger will complain
     for index, filename in enumerate(input_filenames):
         if not has_gsub_table(filename):
             input_filenames[index] = add_gsub_to_font(filename)
 
-    # Merge the fonts together
     merger = merge.Merger()
     font = merger.merge(input_filenames)
 
-    # Use the line metrics defined by the first font
+    # Use the line metrics defined by the first font, which is
+    # supposed to be the basic NotoSans
     metrics = read_line_metrics(ttLib.TTFont(input_filenames[0]))
     set_line_metrics(font, metrics)
 
+    # Select the subset we care about
+    options = subset.Options(ignore_missing_unicodes=False)
+    subsetter = subset.Subsetter(options)
+    unicodes = []
+    with open(ranges_filename) as ranges:
+        for line in ranges:
+            unicodes.extend(parse_unicodes(line.split("#")[0]))
+    if len(unicodes) != 0:
+        subsetter.populate(unicodes=unicodes)
+        subsetter.subset(font)
+
     # Rename the result
     for record in font['name'].names:
         if record.nameID == 1: