giscanner: speed up SourceScanner().parse_files()

Was looking around a bit and noticed about 2/3 of
g-ir-scanner time is spent in SourceScanner().parse_files().

Some profiling quickly shows most of that 2/3 is used
by gi_source_scanner_add_symbol() where it creates a whole
bunch of GFile instances just to compare paths and throw
them away again. With this a scanner instance now maintains
a hash table of GFile instances instead of a list of file
names, so comparing those paths can be reduced to a fast
g_hash_table_contains() call.

This makes "g-ir-scanner <whole_bunch_of_options> --output Gtk-3.0.gir"
complete in about 10 seconds on my box instead of about
30 seconds (both best of 3 runs).

https://bugzilla.gnome.org/show_bug.cgi?id=710320

1 files changed, 7 insertions, 5 deletions

diff --git a/giscanner/giscannermodule.c b/giscanner/giscannermodule.c
index 182d8438..2f4c0e8a 100644
--- a/giscanner/giscannermodule.c
+++ b/giscanner/giscannermodule.c
@@ -356,12 +356,13 @@ pygi_source_scanner_append_filename (PyGISourceScanner *self,
 				     PyObject          *args)
 {
   char *filename;
+  GFile *file;
 
   if (!PyArg_ParseTuple (args, "s:SourceScanner.append_filename", &filename))
     return NULL;
 
-  self->scanner->filenames = g_list_append (self->scanner->filenames,
-					    g_realpath (filename));
+  file = g_file_new_for_path (g_realpath (filename));
+  g_hash_table_add (self->scanner->files, file);
 
   Py_INCREF (Py_None);
   return Py_None;
@@ -511,18 +512,19 @@ pygi_source_scanner_lex_filename (PyGISourceScanner *self,
 				  PyObject          *args)
 {
   char *filename;
+  GFile *file;
 
   if (!PyArg_ParseTuple (args, "s:SourceScanner.lex_filename", &filename))
     return NULL;
 
-  self->scanner->current_filename = g_realpath (filename);
+  self->scanner->current_file = g_file_new_for_path ( g_realpath (filename));
   if (!gi_source_scanner_lex_filename (self->scanner, filename))
     {
       g_print ("Something went wrong during lexing.\n");
       return NULL;
     }
-  self->scanner->filenames =
-    g_list_append (self->scanner->filenames, g_strdup (filename));
+  file = g_file_new_for_path (filename);
+  g_hash_table_add (self->scanner->files, file);
 
   Py_INCREF (Py_None);
   return Py_None;