Remove full story paragraphs if we aren't going to use them.

[dead/lwn-epub.git] / src / LWN / Page.hs

diff --git a/src/LWN/Page.hs b/src/LWN/Page.hs
index c61bf6a5c028dd55e41c71a75748426790dd9885..ccc2590d64b0dddf94dcf85a62a650168549763d 100644 (file)
--- a/src/LWN/Page.hs
+++ b/src/LWN/Page.hs
@@ -42,7 +42,7 @@ import Text.XML.HXT.Core (
   when)
 import Text.HandsomeSoup (css, parseHtml)
 
-import Configuration (Cfg)
+import Configuration (Cfg, full_stories)
 import LWN.Article
 import LWN.HTTP (
   ImageMap,
@@ -58,6 +58,7 @@ import LWN.XHTML (
   is_image,
   preprocess,
   remove_byline,
+  remove_full_story_paragraphs,
   remove_title,
   to_xhtml,
   to_xml,
@@ -134,7 +135,7 @@ insert_full_stories story_map =
     article_xml :: (ArrowXml a) => a XmlTree XmlTree
     article_xml =
       lookup_func
-      $<
+      $< -- From HXT's Control.Arrow.ArrowList
       (this /> full_story_link >>> getAttrValue "href")
                    
 replace_remote_img_srcs :: (ArrowXml a) => ImageMap -> a XmlTree XmlTree
@@ -192,8 +193,12 @@ download_full_stories cfg xml = do
 
 parse :: Cfg -> IOSArrow XmlTree XmlTree -> IO (Maybe Page)
 parse cfg xml = do
-  story_map <- download_full_stories cfg xml
-  let fs_xml = xml >>> insert_full_stories story_map
+  fs_xml <- if (full_stories cfg) then do
+             story_map <- download_full_stories cfg xml
+             return $ xml >>> insert_full_stories story_map
+           else do
+             -- Get rid of them if we don't want them.
+             return $ xml >>> remove_full_story_paragraphs
 
   let clean_xml = fs_xml >>> preprocess
   image_map <- download_images clean_xml
@@ -261,8 +266,6 @@ ap_parse_articles xml = do
   parsed_byline   <- parse_byline xml
   parsed_body     <- ap_parse_body xml
 
-  putStrLn $ fromJust parsed_headline
-
   if (isNothing parsed_headline) || (isNothing parsed_body)
   then return []
   else do