diff options
author | Jesse Rosenthal <jrosenthal@jhu.edu> | 2017-12-30 08:21:42 -0500 |
---|---|---|
committer | Jesse Rosenthal <jrosenthal@jhu.edu> | 2017-12-30 08:21:42 -0500 |
commit | 4fc3f511863c578be6a3237d02133da25db0ce05 (patch) | |
tree | 5e84bddfb48cdbef4c5aa87395f7545fb4838eaa /src/Text/Pandoc | |
parent | f654c2022f5625d98b1a8b746a7be9197deda747 (diff) | |
download | pandoc-4fc3f511863c578be6a3237d02133da25db0ce05.tar.gz |
Docx reader: Read multiple children of w:sdtContents`
Previously we had only read the first child of an sdtContents tag. Now
we replace sdt with all children of the sdtContents tag.
This changes the expected test result of our nested_anchors test,
since now we read docx's generated TOCs.
Diffstat (limited to 'src/Text/Pandoc')
-rw-r--r-- | src/Text/Pandoc/Readers/Docx/Parse.hs | 14 |
1 files changed, 9 insertions, 5 deletions
diff --git a/src/Text/Pandoc/Readers/Docx/Parse.hs b/src/Text/Pandoc/Readers/Docx/Parse.hs index 48a512be2..071f901b6 100644 --- a/src/Text/Pandoc/Readers/Docx/Parse.hs +++ b/src/Text/Pandoc/Readers/Docx/Parse.hs @@ -118,17 +118,21 @@ mapD f xs = in concatMapM handler xs -unwrapSDT :: NameSpaces -> Content -> Content +unwrapSDT :: NameSpaces -> Content -> [Content] unwrapSDT ns (Elem element) | isElem ns "w" "sdt" element , Just sdtContent <- findChildByName ns "w" "sdtContent" element - , child : _ <- elChildren sdtContent - = Elem child -unwrapSDT _ content = content + = map Elem $ elChildren sdtContent +unwrapSDT _ content = [content] + +unwrapSDTchild :: NameSpaces -> Content -> Content +unwrapSDTchild ns (Elem element) = + Elem $ element { elContent = concatMap (unwrapSDT ns) (elContent element) } +unwrapSDTchild _ content = content walkDocument' :: NameSpaces -> XMLC.Cursor -> XMLC.Cursor walkDocument' ns cur = - let modifiedCur = XMLC.modifyContent (unwrapSDT ns) cur + let modifiedCur = XMLC.modifyContent (unwrapSDTchild ns) cur in case XMLC.nextDF modifiedCur of Just cur' -> walkDocument' ns cur' |