Check invalid characters on some recipe metadata

index 9c05c86..fc16540 100644
@@ -11,6 +11,7 @@
 #  -Check if packages contains .debug directories or .so files
 #   where they should be in -dev or -dbg
 #  -Check if config.log contains traces to broken autoconf tests
+#  -Check invalid characters (non-utf8) on some package metadata
 #  -Ensure that binaries in base_[bindir|sbindir|libdir] do not link
 #   into exec_prefix
 #  -Check that scripts in base_[bindir|sbindir|libdir] do not reference

@@ -36,7 +37,7 @@ WARN_QA ?= "ldflags useless-rpaths rpaths staticdev libdir xorg-driver-abi \
 ERROR_QA ?= "dev-so debug-deps dev-deps debug-files arch pkgconfig la \
             perms dep-cmp pkgvarcheck perm-config perm-line perm-link \
             split-strip packages-list pkgv-undefined var-undefined \
-            version-going-backwards expanded-d \
+            version-going-backwards expanded-d invalid-chars \
             "
 
 ALL_QA = "${WARN_QA} ${ERROR_QA}"

@@ -947,6 +948,24 @@ def package_qa_check_expanded_d(path,name,d,elf,messages):
                         sane = False
     return sane
 
+def package_qa_check_encoding(keys, encode, d):
+    def check_encoding(key,enc):
+        sane = True
+        value = d.getVar(key, True)
+        if value:
+            try:
+                s = unicode(value, enc)
+            except UnicodeDecodeError as e:
+                error_msg = "%s has non %s characters" % (key,enc)
+                sane = False
+                package_qa_handle_error("invalid-chars", error_msg, d)
+        return sane
+
+    for key in keys:
+        sane = check_encoding(key, encode)
+        if not sane:
+            break
+
 # The PACKAGE FUNC to scan each package
 python do_package_qa () {
     import subprocess

@@ -956,6 +975,9 @@ python do_package_qa () {
 
     bb.build.exec_func("read_subpackage_metadata", d)
 
+    # Check non UTF-8 characters on recipe's metadata
+    package_qa_check_encoding(['DESCRIPTION', 'SUMMARY', 'LICENSE', 'SECTION'], 'utf-8', d)
+
     logdir = d.getVar('T', True)
     pkg = d.getVar('PN', True)
 

index 9e1ed28..398ceee 100644
@@ -96,9 +96,8 @@ python do_package_deb () {
         bb.utils.mkdirhier(controldir)
         os.chmod(controldir, 0755)
         try:
-            ctrlfile = open(os.path.join(controldir, 'control'), 'w')
-            # import codecs
-            # ctrlfile = codecs.open("someFile", "w", "utf-8")
+            import codecs
+            ctrlfile = codecs.open(os.path.join(controldir, 'control'), 'w', 'utf-8')
         except OSError:
             bb.utils.unlockfile(lf)
             raise bb.build.FuncFailed("unable to open control file for writing.")

@@ -149,7 +148,7 @@ python do_package_deb () {
                 # Special behavior for description...
                 if 'DESCRIPTION' in fs:
                      summary = localdata.getVar('SUMMARY', True) or localdata.getVar('DESCRIPTION', True) or "."
-                     ctrlfile.write('Description: %s\n' % unicode(summary))
+                     ctrlfile.write('Description: %s\n' % unicode(summary,'utf-8'))
                      description = localdata.getVar('DESCRIPTION', True) or "."
                      description = textwrap.dedent(description).strip()
                      if '\\n' in description:

@@ -158,19 +157,24 @@ python do_package_deb () {
                              # We don't limit the width when manually indent, but we do
                              # need the textwrap.fill() to set the initial_indent and
                              # subsequent_indent, so set a large width
-                             ctrlfile.write('%s\n' % unicode(textwrap.fill(t, width=100000, initial_indent=' ', subsequent_indent=' ')))
+                             ctrlfile.write('%s\n' % unicode(textwrap.fill(t, width=100000, initial_indent=' ', subsequent_indent=' '),'utf-8'))
                      else:
                          # Auto indent
-                         ctrlfile.write('%s\n' % unicode(textwrap.fill(description.strip(), width=74, initial_indent=' ', subsequent_indent=' ')))
+                         ctrlfile.write('%s\n' % unicode(textwrap.fill(description.strip(), width=74, initial_indent=' ', subsequent_indent=' '),'utf-8'))
 
                 else:
-                     ctrlfile.write(unicode(c % tuple(pullData(fs, localdata))))
+                     ctrlfile.write(unicode(c % tuple(pullData(fs, localdata)),'utf-8'))
         except KeyError:
             import sys
             (type, value, traceback) = sys.exc_info()
             bb.utils.unlockfile(lf)
             ctrlfile.close()
             raise bb.build.FuncFailed("Missing field for deb generation: %s" % value)
+        except UnicodeDecodeError:
+            bb.utils.unlockfile(lf)
+            ctrlfile.close()
+            raise bb.build.FuncFailed("Non UTF-8 characters found in one of the fields")
+
         # more fields
 
         custom_fields_chunk = get_package_additional_metadata("deb", localdata)