If we don't have the contents of a particular full story, drop its paragraph.

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

diff --git a/src/LWN/Page.hs b/src/LWN/Page.hs
index 49faa0bb4d6d1b0c77c0b4c6eb8d00e1a9261c50..30c54b550a530777eb9ccfd818b16785c46cc0ef 100644 (file)
--- a/src/LWN/Page.hs
+++ b/src/LWN/Page.hs
@@ -34,6 +34,7 @@ import Text.XML.HXT.Core (
   getChildren,
   getText,
   hasName,
+  none,
   processAttrl,
   processTopDown,
   this,
@@ -42,7 +43,7 @@ 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 +59,7 @@ import LWN.XHTML (
   is_image,
   preprocess,
   remove_byline,
+  remove_full_story_paragraphs,
   remove_title,
   to_xhtml,
   to_xml,
@@ -127,14 +129,14 @@ insert_full_stories story_map =
     lookup_func :: (ArrowXml a) => URL -> a XmlTree XmlTree
     lookup_func href =
       case Map.lookup href story_map of
-        -- Leave it alone if we don't have the full story.
-        Nothing -> this
+        -- Drop the paragraph if we don't have the contents.
+        Nothing -> none
         Just v -> to_xml v
 
     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 +194,12 @@ 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