[libsoup] tld-parser: Rewrite in Python

[Colin Walters <walters src gnome org>]

commit 29345a6d6b181956d3eaffe8d068aca63654e4cb
Author: Colin Walters <walters verbum org>
Date:   Tue Jun 26 13:27:17 2012 -0400

    tld-parser: Rewrite in Python
    
    This avoids the issues in building native code to build an
    intermediate file to build more native code.  Automake has
    BUILT_SOURCES but it's easier to just have build tools in scripting
    languages.
    
    https://bugzilla.gnome.org/show_bug.cgi?id=678909

 libsoup/Makefile.am   |   14 ++----
 libsoup/tld-parser.c  |  101 -------------------------------------------------
 libsoup/tld-parser.py |   44 +++++++++++++++++++++
 3 files changed, 49 insertions(+), 110 deletions(-)
---
diff --git a/libsoup/Makefile.am b/libsoup/Makefile.am
index 6997371..fdba1ef 100644
--- a/libsoup/Makefile.am
+++ b/libsoup/Makefile.am
@@ -1,5 +1,7 @@
 ## Process this file with automake to produce Makefile.in
 
+EXTRA_DIST =
+
 include $(GLIB_MAKEFILE)
 
 if OS_WIN32
@@ -81,7 +83,6 @@ libsoup_2_4_la_LIBADD =			\
 	$(LIBWS2_32)
 
 libsoup_2_4_la_SOURCES =		\
-	tld_data.inc			\
 	soup-address.c			\
 	soup-auth.c			\
 	soup-auth-basic.h		\
@@ -171,17 +172,12 @@ libsoup_2_4_la_SOURCES =		\
 	soup-xmlrpc.c
 
 # TLD rules
-noinst_PROGRAMS = 	\
-	tld-parser
-
-tld_parser_SOURCES = tld-parser.c
-tld_parser_CFLAGS = $(GLIB_CFLAGS)
-tld_parser_LDADD = $(GLIB_LIBS)
+EXTRA_DIST += tld-parser.py
 
 TLD_DATA_FILE=$(top_srcdir)/data/effective_tld_names.dat
 
-tld_data.inc: tld-parser $(TLD_DATA_FILE)
-	$(builddir)/tld-parser $(TLD_DATA_FILE) tld_data.inc
+tld_data.inc: tld-parser.py $(TLD_DATA_FILE)
+	$(srcdir)/tld-parser.py $(TLD_DATA_FILE) tld_data.inc
 
 if BUILD_LIBSOUP_GNOME
 
diff --git a/libsoup/tld-parser.py b/libsoup/tld-parser.py
new file mode 100755
index 0000000..469f721
--- /dev/null
+++ b/libsoup/tld-parser.py
@@ -0,0 +1,44 @@
+#!/usr/bin/env python
+
+# Generate tld rules
+# Copyright (C) 2012 Red Hat, Inc.
+# Based on tld-parser.c Copyright (C) 2012 Igalia S.L.
+
+import os,sys
+
+SOUP_TLD_RULE_NORMAL = 0
+SOUP_TLD_RULE_MATCH_ALL = 1 << 0
+SOUP_TLD_RULE_EXCEPTION = 1 << 1
+
+tlds_file = open(sys.argv[1])
+inc_file = open(sys.argv[2], 'w')
+
+first = True
+for rule in tlds_file:
+    rule = rule.strip()
+    if rule == '' or rule.startswith('//'):
+        continue
+    domain = rule
+    flags = 0
+    if rule[0] == '!':
+        domain = domain[1:]
+        flags |= SOUP_TLD_RULE_EXCEPTION
+
+    if domain.startswith('*.'):
+        domain = domain[2:]
+        flags |= SOUP_TLD_RULE_MATCH_ALL
+    
+    if domain.startswith('.'):
+        domain = domain[1:]
+
+    if not first:
+	inc_file.write(',\n')
+    else:
+	first = False
+    inc_file.write('{ "%s", %d }' % (domain.strip(), flags))
+
+inc_file.write('\n')
+
+tlds_file.close()
+inc_file.close()
+