www/server/source/sitemap-generator sitemap-gen...

[Pavel Kharitonov]

CVSROOT:        /web/www
Module name:    www
Changes by:     Pavel Kharitonov <ineiev>       13/03/14 14:29:29

Modified files:
        server/source/sitemap-generator: sitemap-generator.py 
Added files:
        server/source/sitemap-generator: index_files 

Log message:
        Load non-default index filenames from a file RT #811230.

CVSWeb URLs:
http://web.cvs.savannah.gnu.org/viewcvs/www/server/source/sitemap-generator/sitemap-generator.py?cvsroot=www&r1=1.6&r2=1.7
http://web.cvs.savannah.gnu.org/viewcvs/www/server/source/sitemap-generator/index_files?cvsroot=www&rev=1.1

Patches:
Index: sitemap-generator.py
===================================================================
RCS file: /web/www/www/server/source/sitemap-generator/sitemap-generator.py,v
retrieving revision 1.6
retrieving revision 1.7
diff -u -b -r1.6 -r1.7
--- sitemap-generator.py        1 Feb 2013 14:47:48 -0000       1.6
+++ sitemap-generator.py        14 Mar 2013 14:29:28 -0000      1.7
@@ -64,6 +64,7 @@
 title_tails = None
 replacement_titles = None
 translations = {}
+index_filenames = {}
 
 def is_directory_empty(path):
        directory_contents = get_directory_contents(path)
@@ -130,6 +131,8 @@
        return {'files': files, 'subdirectories': subdirs}
        
 def get_index_filename(directory):
+       if directory in index_filenames:
+               return index_filenames[directory]
        # We only want either directoryname.html or index.html files.
        # If both are present, don't use either, and output an error,
        # so it can be resolved.
@@ -479,6 +482,24 @@
        
        return file_contents
        
+def load_index_filenames(filename):
+       filenames = {}
+       fd = open(filename, 'r')
+       lines = fd.read().splitlines()
+       fd.close()
+       for line in lines:
+               line = re.sub('^\s*', '', line)
+               line = re.sub('\s*$', '', line)
+               if line[0] == '#':
+                       continue
+               pos = line.rfind('/')
+               if pos < 1:
+                       continue
+               name = line[pos + 1: ]  
+               directory = line[: pos]
+               filenames[directory] = name
+       return filenames
+       
 def escape_spaces(regexp_list):
        new_regexp_list = []
        
@@ -513,6 +534,7 @@
   read_file('directories_to_print_regardless_of_emptiness').splitlines()
 excluded_dirs = read_file('directories_to_skip').splitlines()
 excluded_files = read_file('files_to_skip').splitlines()
+index_filenames = load_index_filenames('index_files')
 title_tails = \
   escape_spaces(read_file('regexps_removed_from_titles').splitlines())
 replacement_titles = load_replacement_titles()

Index: index_files
===================================================================
RCS file: index_files
diff -N index_files
--- /dev/null   1 Jan 1970 00:00:00 -0000
+++ index_files 14 Mar 2013 14:29:28 -0000      1.1
@@ -0,0 +1 @@
+fun/humor.html