Hardcode the blanks in the library

https://bugs.freedesktop.org/show_bug.cgi?id=79956

3 files changed, 190 insertions, 0 deletions

diff --git a/fc-blanks/Makefile.am b/fc-blanks/Makefile.am
new file mode 100644
index 00000000..f9c2486f
--- /dev/null
+++ b/fc-blanks/Makefile.am
@@ -0,0 +1,40 @@
+# -*- encoding: utf-8 -*-
+#
+# Copyright © 2003  Keith Packard
+#
+# Permission to use, copy, modify, distribute, and sell this software and its
+# documentation for any purpose is hereby granted without fee, provided that
+# the above copyright notice appear in all copies and that both that
+# copyright notice and this permission notice appear in supporting
+# documentation, and that the name of the author(s) not be used in
+# advertising or publicity pertaining to distribution of the software without
+# specific, written prior permission.  The authors make no
+# representations about the suitability of this software for any purpose.  It
+# is provided "as is" without express or implied warranty.
+#
+# THE AUTHOR(S) DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
+# INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO
+# EVENT SHALL THE AUTHOR(S) BE LIABLE FOR ANY SPECIAL, INDIRECT OR
+# CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE,
+# DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
+# TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
+# PERFORMANCE OF THIS SOFTWARE.
+
+NULL =
+BLANKSPY = fc-blanks.py
+BLANKS_H = fcblanks.h
+TMPL = fcblanks.tmpl.h
+noinst_SCRIPTS = $(BLANKSPY)
+noinst_HEADERS = $(BLANKS_H)
+
+$(BLANKS_H): $(BLANKSPY) $(TMPL)
+	$(AM_V_GEN) $(PYTHON) $(BLANKSPY) < $(TMPL) > $(BLANKS_H).tmp && \
+	mv $(BLANKS_H).tmp $(BLANKS_H) || ($(RM) $(BLANKS_H).tmp && false)
+
+EXTRA_DIST = 		\
+	$(BLANKS_H)	\
+	$(TMPL)		\
+	$(NULL)
+DISTCLEANFILES = $(BLANKS_H)
+
+-include $(top_srcdir)/git.mk
diff --git a/fc-blanks/fc-blanks.py b/fc-blanks/fc-blanks.py
new file mode 100755
index 00000000..fb01614f
--- /dev/null
+++ b/fc-blanks/fc-blanks.py
@@ -0,0 +1,125 @@
+#! /usr/bin/python
+
+import urllib2
+import sys
+from lxml import html
+
+fp = urllib2.urlopen('http://unicode.org/cldr/utility/list-unicodeset.jsp?a=[%3AGC%3DZs%3A][%3ADI%3A]&abb=on&ucd=on&esc=on&g')
+data = fp.read()
+fp.close()
+
+dom = html.fromstring(data)
+x = dom.xpath('/html/body/form/p/text()')
+p = x[1]
+if p[0] == '[' and p[-1] == ']':
+    p = p.replace('[', '').replace(']', '')
+else:
+    sys.exit(1)
+fescape = False
+funicode = False
+frange = False
+fprocess = False
+v = 0
+vbegin = 0
+vend = 0
+n = 0
+l = []
+
+def insert(db, begin, end):
+    db.append([begin, end])
+
+for i in p:
+    if i == '\\':
+        if n > 0:
+            if frange == True and funicode == True:
+                vend = v
+                insert(l, vbegin, vend)
+                fprocess = True
+            elif funicode == True:
+                vbegin = v
+                vend = v
+                insert(l, vbegin, vend)
+                fprocess = True
+        funicode = False
+        fescape = True
+    elif i.lower() == 'u' and fescape == True:
+        funicode = True
+    elif i >= '0' and i <= '9' or i.lower() >= 'a' and i.lower() <= 'f':
+        if funicode == True:
+            v <<= 4
+            v += int(i, 16)
+        else:
+            raise RuntimeError, "Unable to parse Unicode"
+    elif i == ' ':
+        if frange == True and funicode == True:
+            vend = v
+            insert(l, vbegin, vend)
+            fprocess = True
+        elif funicode == True:
+            vbegin = v
+            vend = v
+            insert(l, vbegin, vend)
+            fprocess = True
+        fescape = False
+        funicode = False
+        frange = False
+    elif i == '-':
+        vbegin = v
+        v = 0
+        fescape = False
+        funicode = False
+        frange = True
+    else:
+        raise RuntimeError, "Unable to parse Unicode: %s" % i
+
+    if fprocess == True:
+        vbegin = 0
+        vend = 0
+        v = 0
+        fprocess = False
+        funicode = False
+        frange = False
+    n += 1
+
+if frange == True and funicode == True:
+    vend = v
+    insert(l, vbegin, vend)
+elif funicode == True:
+    vbegin = vend = v
+    insert(l, vbegin, vend)
+
+# somewhat missing 0x0020 in the list of code from Unicode Utilities
+insert(l, 0x0020, 0x0020)
+ncode = 0
+for i in l:
+    ncode += (i[1] - i[0] + 1)
+
+a = int(x[0].split(' ')[0].replace(',', ''))
+if a != ncode:
+    sys.stderr.write("Unexpected the amount of code points: %d (expected %d)\n" % (ncode, a))
+    sys.exit(1)
+insert(l, 0x2800, 0x2800)
+
+while True:
+    s = sys.stdin.readline().rstrip()
+    if s == "@@@":
+        break
+    print s
+
+print "static FcChar32 _fcBlanks[%s] = {" % (ncode + 1)
+k = 0
+for i in sorted(l, key=lambda(a): a[0]):
+    for j in range(i[0], i[1] + 1):
+        if k != 0:
+            print ","
+        print "    0x%04x" % j,
+        k += 1
+
+print "};"
+print '''
+static FcBlanks fcBlanks = {
+    %s,
+    -1,
+    _fcBlanks
+};
+''' % (ncode + 1)
diff --git a/fc-blanks/fcblanks.tmpl.h b/fc-blanks/fcblanks.tmpl.h
new file mode 100644
index 00000000..2bcaa21d
--- /dev/null
+++ b/fc-blanks/fcblanks.tmpl.h
@@ -0,0 +1,25 @@
+/*
+ * fontconfig/fc-blanks/fcblanks.tmpl.h
+ *
+ * Copyright © 2003 Keith Packard
+ *
+ * Permission to use, copy, modify, distribute, and sell this software and its
+ * documentation for any purpose is hereby granted without fee, provided that
+ * the above copyright notice appear in all copies and that both that
+ * copyright notice and this permission notice appear in supporting
+ * documentation, and that the name of the author(s) not be used in
+ * advertising or publicity pertaining to distribution of the software without
+ * specific, written prior permission.  The authors make no
+ * representations about the suitability of this software for any purpose.  It
+ * is provided "as is" without express or implied warranty.
+ *
+ * THE AUTHOR(S) DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
+ * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO
+ * EVENT SHALL THE AUTHOR(S) BE LIABLE FOR ANY SPECIAL, INDIRECT OR
+ * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE,
+ * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
+ * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
+ * PERFORMANCE OF THIS SOFTWARE.
+ */
+
+@@@