Allow UTF-8 input for name entries

c/makeotf/makeotf_lib/api/hotconv.h

@@ -12,7 +12,7 @@ This software is licensed as OpenSource, under the Apache License, Version 2.0.
 extern "C" {
 #endif
 
-#define HOT_VERSION 0x010071 /* Library version (1.0.113) */
+#define HOT_VERSION 0x010072 /* Library version (1.0.114) */
 /* Major, minor, build = (HOT_VERSION >> 16) & 0xff, (HOT_VERSION >> 8) & 0xff, HOT_VERSION & 0xff) */
 /* Warning: this string is now part of heuristic used by CoolType to identify the
 first round of CoolType fonts which had the backtrack sequence of a chaining

c/makeotf/makeotf_lib/build/hotpccts/featgram.g

@@ -139,7 +139,7 @@ hotCtx g;
 #token	"\r\n"		<<zzskip(); zzline++;>>
 #token	"[\r\n]"	<<zzskip(); zzline++;>>
 
-#token "[\0x20-\0x7E]"  <<featAddNameStringChar(zzlextext[0]); zzskip();>>
+#token "[\0x20-\0x7E\0x80-\0xF7]"  <<featAddNameStringChar(zzlextext[0]); zzskip();>>
 
 #lexclass START // ------------------------------------------------------------
 

c/makeotf/makeotf_lib/source/hotconv/featerr.c

@@ -79,7 +79,7 @@ ANTLRChar *zztokens[159] = {
     /* 27 */ "\"",
     /* 28 */ "\\r\\n",
     /* 29 */ "[\\r\\n]",
-    /* 30 */ "[\\0x20-\\0x7E]",
+    /* 30 */ "[\\0x20-\\0x7E\\0x80-\\0xF7]",
     /* 31 */ "#~[\\r\\n]*",
     /* 32 */ "[\\ \\t]+",
     /* 33 */ "\\r\\n",

c/makeotf/makeotf_lib/source/hotconv/featpars.dlg

@@ -984,7 +984,7 @@ include
     zzskip(); zzline++;  
 	>>
 
-[\0x20-\0x7E]
+[\0x20-\0x7E\0x80-\0xF7]
 	<<
 		NLA = 30;
     featAddNameStringChar(zzlextext[0]); zzskip();  

c/makeotf/makeotf_lib/source/hotconv/featscan.c

@@ -1038,19 +1038,19 @@ static unsigned char shift7[257] = {
     4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
     4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
     4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
-    4, 4, 4, 4, 4, 4, 4, 4, 5, 5,
-    5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
-    5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
-    5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
-    5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
-    5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
-    5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
-    5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
-    5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
-    5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
-    5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
-    5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
-    5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
+    4, 4, 4, 4, 4, 4, 4, 4, 5, 4,
+    4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
+    4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
+    4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
+    4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
+    4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
+    4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
+    4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
+    4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
+    4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
+    4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
+    4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
+    4, 4, 4, 4, 4, 4, 4, 4, 4, 5,
     5, 5, 5, 5, 5, 5, 5};
 
 #define DfaStates 976

c/makeotf/makeotf_lib/source/hotconv/feattoks.h

@@ -1,6 +1,6 @@
 #ifndef feattoks_h
 #define feattoks_h
-/* feattoks.h -- List of labeled tokens and stuff
+/* feattoks.h -- List of labelled tokens and stuff
  *
  * Generated from: featgram.g
  *

c/makeotf/makeotf_lib/source/hotconv/hot.c

@@ -1429,6 +1429,10 @@ static int prepMacName(hotCtx g, char *src) {
         int actn;       /* Action flags */
         int c = *src++;
 
+        /* Direct UTF-8 input is not supported. */
+        if (c < 0)
+            return 1;
+
         switch (c) {
             case '\\':
                 class = 0;

c/makeotf/source/main.c

@@ -30,7 +30,7 @@
 
 jmp_buf mark;
 
-#define MAKEOTF_VERSION "2.5.65598"
+#define MAKEOTF_VERSION "2.5.65599"
 /* Warning: this string is now part of heuristic used by CoolType to identify the
    first round of CoolType fonts which had the backtrack sequence of a chaining
    contextual substitution ordered incorrectly.  Fonts with the old ordering MUST match

docs/OpenTypeFeatureFileSpecification.md

@@ -3289,16 +3289,16 @@ that are assigned.
     nameid 1 1 <string>;        1   1           0           0
     nameid 1 1 S L <string>;    1   1           S           L
 
-A string is composed of 1-byte ASCII characters enclosed by ASCII double quote
+A string is composed of UTF-8 characters enclosed by ASCII double quote
 characters (`"`). Newlines embedded within the string are removed from the
 character sequence to be stored.
 
-Strings are converted to Unicode for the Windows platform by adding a high byte
-of 0. 2-byte Unicode values for the Windows platform may be specified using a
-special character sequence of a backslash character (`\`) followed by exactly
-four hexadecimal numbers (of either case) which may not all be zero, e.g. \4e2d.
-The ASCII backslash character must be represented as the sequence \005c or \005C
-and the ASCII double quote character must be represented as the sequence \0022.
+Strings are converted to UTF-16 for the Windows platform. Unicode values for
+the Windows platform may also be specified using a special character sequence
+of a backslash character (`\`) followed by exactly four hexadecimal numbers (of
+either case) which may not all be zero, e.g. \4e2d.  The ASCII backslash
+character must be represented as the sequence \005c or \005C and the ASCII
+double quote character must be represented as the sequence \0022.
 
 There is no corresponding conversion to Unicode for the Macintosh platform but
 character codes in the range 128-255 may be specified using a special character
@@ -3311,7 +3311,13 @@ double quote character must be represented as the sequence \22.
 
 ```fea
 table name {
-    nameid 9 "Joachim M\00fcller-Lanc\00e9";    # Windows (Unicode)
+    nameid 9 "Joachim Müller-Lancé";            # Windows (Unicode), UTF-8 input
+} name;
+```
+
+```fea
+table name {
+    nameid 9 "Joachim M\00fcller-Lanc\00e9";    # Windows (Unicode), escaped Unicode values
     nameid 9 1 "Joachim M\9fller-Lanc\8e";      # Macintosh (Mac Roman)
 } name;
 ```

python/afdko/makeotf.py

@@ -25,7 +25,7 @@
 """
 
 __version__ = """\
-makeotf.py v2.7.10 Dec 3 2019
+makeotf.py v2.7.11 May 20 2020
 """
 
 __methods__ = """

requirements.txt

@@ -7,7 +7,7 @@ booleanOperations==0.9.0
 cu2qu[cli]==1.6.7
 defcon[lxml,pens]==0.6.0
 fontMath==0.6.0
-fontTools[unicode,lxml,ufo,woff]==4.10.0
+fontTools[unicode,lxml,ufo,woff]==4.10.2
 mutatorMath==3.0.1
 psautohint==2.0.1
 ufonormalizer==0.4.1

tests/buildcff2vf_data/expected_output/GSUBVar.ttx

@@ -324,31 +324,31 @@
 
     <!-- Regular -->
     <!-- PostScript: SourceCodeRoman-Regular -->
-    <NamedInstance flags="0x0" postscriptNameID="262" subfamilyNameID="261">
+    <NamedInstance flags="0x0" postscriptNameID="261" subfamilyNameID="2">
       <coord axis="wght" value="400.0"/>
     </NamedInstance>
 
     <!-- Medium -->
     <!-- PostScript: SourceCodeRoman-Medium -->
-    <NamedInstance flags="0x0" postscriptNameID="264" subfamilyNameID="263">
+    <NamedInstance flags="0x0" postscriptNameID="263" subfamilyNameID="262">
       <coord axis="wght" value="500.0"/>
     </NamedInstance>
 
     <!-- Semibold -->
     <!-- PostScript: SourceCodeRoman-Semibold -->
-    <NamedInstance flags="0x0" postscriptNameID="266" subfamilyNameID="265">
+    <NamedInstance flags="0x0" postscriptNameID="265" subfamilyNameID="264">
       <coord axis="wght" value="600.0"/>
     </NamedInstance>
 
     <!-- Bold -->
     <!-- PostScript: SourceCodeRoman-Bold -->
-    <NamedInstance flags="0x0" postscriptNameID="268" subfamilyNameID="267">
+    <NamedInstance flags="0x0" postscriptNameID="267" subfamilyNameID="266">
       <coord axis="wght" value="700.0"/>
     </NamedInstance>
 
     <!-- Black -->
     <!-- PostScript: SourceCodeRoman-Black -->
-    <NamedInstance flags="0x0" postscriptNameID="270" subfamilyNameID="269">
+    <NamedInstance flags="0x0" postscriptNameID="269" subfamilyNameID="268">
       <coord axis="wght" value="900.0"/>
     </NamedInstance>
   </fvar>

tests/makeotfexe_data/expected_output/spec/9e-14.ttx

@@ -0,0 +1,46 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ttFont>
+
+  <name>
+    <namerecord nameID="1" platformID="1" platEncID="0" langID="0x0" unicode="True">
+      Untitled1
+    </namerecord>
+    <namerecord nameID="2" platformID="1" platEncID="0" langID="0x0" unicode="True">
+      Regular
+    </namerecord>
+    <namerecord nameID="3" platformID="1" platEncID="0" langID="0x0" unicode="True">
+      1.000;UKWN;Untitled1
+    </namerecord>
+    <namerecord nameID="4" platformID="1" platEncID="0" langID="0x0" unicode="True">
+      Untitled1
+    </namerecord>
+    <namerecord nameID="5" platformID="1" platEncID="0" langID="0x0" unicode="True">
+
+    </namerecord>
+    <namerecord nameID="6" platformID="1" platEncID="0" langID="0x0" unicode="True">
+      Untitled1
+    </namerecord>
+    <namerecord nameID="1" platformID="3" platEncID="1" langID="0x409">
+      Untitled1
+    </namerecord>
+    <namerecord nameID="2" platformID="3" platEncID="1" langID="0x409">
+      Regular
+    </namerecord>
+    <namerecord nameID="3" platformID="3" platEncID="1" langID="0x409">
+      1.000;UKWN;Untitled1
+    </namerecord>
+    <namerecord nameID="4" platformID="3" platEncID="1" langID="0x409">
+      Untitled1
+    </namerecord>
+    <namerecord nameID="5" platformID="3" platEncID="1" langID="0x409">
+
+    </namerecord>
+    <namerecord nameID="6" platformID="3" platEncID="1" langID="0x409">
+      Untitled1
+    </namerecord>
+    <namerecord nameID="9" platformID="3" platEncID="1" langID="0x409">
+      Joachim Müller-Lancé
+    </namerecord>
+  </name>
+
+</ttFont>

tests/makeotfexe_data/input/spec/9e-14.fea

@@ -0,0 +1,4 @@
+# TABLES: name
+table name {
+   nameid 9 "Joachim Müller-Lancé";    # Windows (Unicode)
+} name;

tests/makeotfexe_data/input/spec/9e-15.bad.fea

@@ -0,0 +1,3 @@
+table name {
+   nameid 9 1 "Joachim Müller-Lancé";  # Macintosh (Mac Roman)
+} name;