Tissevert/pandoc
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

Docx reader: Avoid 0-level headers.

Browse source 
We used to parse paragraphs styled with "HeadingN" as "nth-level
header." But if a document has a custom style named "Heading0", this
will produce a 0-level header, which shouldn't exist. We only parse
this style if N>0. Otherwise we treat it as a normal style name, and
follow its dependencies, if any.

Closes #3830.
This commit is contained in:
Jesse Rosenthal 2017-08-06 19:26:50 -07:00
parent 8164a005c0
commit a36a56b8ac
1 changed files with 5 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
src/Text/Pandoc/Readers/Docx/Parse.hs
View file

@ -61,7 +61,7 @@ import Control.Monad.Reader
import Control.Monad.State.Strict
import Data.Bits ((.|.))
import qualified Data.ByteString.Lazy as B
import Data.Char (chr, isDigit, ord, readLitChar)
import Data.Char (chr, ord, readLitChar)
import Data.List
import qualified Data.Map as M
import Data.Maybe
@ -939,19 +939,18 @@ elemToRunStyle ns element parentStyle
}
elemToRunStyle _ _ _ = defaultRunStyle
isNumericNotNull :: String -> Bool
isNumericNotNull str = (str /= []) && (all isDigit str)
getHeaderLevel :: NameSpaces -> Element -> Maybe (String,Int)
getHeaderLevel ns element
| Just styleId <- findAttrByName ns "w" "styleId" element
, Just index <- stripPrefix "Heading" styleId
, isNumericNotNull index = Just (styleId, read index)
, Just n <- stringToInteger index
, n > 0 = Just (styleId, fromInteger n)
| Just styleId <- findAttrByName ns "w" "styleId" element
, Just index <- findChildByName ns "w" "name" element >>=
findAttrByName ns "w" "val" >>=
stripPrefix "heading "
, isNumericNotNull index = Just (styleId, read index)
, Just n <- stringToInteger index
, n > 0 = Just (styleId, fromInteger n)
getHeaderLevel _ _ = Nothing
blockQuoteStyleIds :: [String]