Docx reader: Change behavior of Super/Subscript

In docx, super- and subscript are attributes of Vertalign. It makes more
sense to follow this, and have different possible values of Vertalign in
runStyle. This is mainly a preparatory step for real style parsing,
since it can distinguish between vertical align being explicitly turned
off and it not being set.

In addition, it makes parsing a bit clearer, and makes sure we don't do
docx-impossible things like being simultaneously super and sub.
This commit is contained in:
Jesse Rosenthal 2014-08-17 08:20:00 -04:00
parent 9d52ecdd42
commit dc5b0ba09b
2 changed files with 17 additions and 16 deletions

View file

@ -257,10 +257,10 @@ runStyleToTransform rPr
smallcaps . (runStyleToTransform rPr {isSmallCaps = Nothing})
| Just True <- isStrike rPr =
strikeout . (runStyleToTransform rPr {isStrike = Nothing})
| isSuperScript rPr =
superscript . (runStyleToTransform rPr {isSuperScript = False})
| isSubScript rPr =
subscript . (runStyleToTransform rPr {isSubScript = False})
| Just SupScrpt <- rVertAlign rPr =
superscript . (runStyleToTransform rPr {rVertAlign = Nothing})
| Just SubScrpt <- rVertAlign rPr =
subscript . (runStyleToTransform rPr {rVertAlign = Nothing})
| Just "single" <- rUnderline rPr =
emph . (runStyleToTransform rPr {rUnderline = Nothing})
| otherwise = id

View file

@ -43,6 +43,7 @@ module Text.Pandoc.Readers.Docx.Parse ( Docx(..)
, Relationship
, Media
, RunStyle(..)
, VertAlign(..)
, ParIndentation(..)
, ParagraphStyle(..)
, Row(..)
@ -196,12 +197,14 @@ data Run = Run RunStyle [RunElem]
data RunElem = TextRun String | LnBrk | Tab
deriving Show
data VertAlign = BaseLn | SupScrpt | SubScrpt
deriving Show
data RunStyle = RunStyle { isBold :: Maybe Bool
, isItalic :: Maybe Bool
, isSmallCaps :: Maybe Bool
, isStrike :: Maybe Bool
, isSuperScript :: Bool
, isSubScript :: Bool
, rVertAlign :: Maybe VertAlign
, rUnderline :: Maybe String
, rStyle :: Maybe String }
deriving Show
@ -211,8 +214,7 @@ defaultRunStyle = RunStyle { isBold = Nothing
, isItalic = Nothing
, isSmallCaps = Nothing
, isStrike = Nothing
, isSuperScript = False
, isSubScript = False
, rVertAlign = Nothing
, rUnderline = Nothing
, rStyle = Nothing
}
@ -677,14 +679,13 @@ elemToRunStyle ns element
, isItalic = checkOnOff ns rPr (elemName ns "w" "i")
, isSmallCaps = checkOnOff ns rPr (elemName ns "w" "smallCaps")
, isStrike = checkOnOff ns rPr (elemName ns "w" "strike")
, isSuperScript =
(Just "superscript" ==
(findChild (elemName ns "w" "vertAlign") rPr >>=
findAttr (elemName ns "w" "val")))
, isSubScript =
(Just "subscript" ==
(findChild (elemName ns "w" "vertAlign") rPr >>=
findAttr (elemName ns "w" "val")))
, rVertAlign =
findChild (elemName ns "w" "vertAlign") rPr >>=
findAttr (elemName ns "w" "val") >>=
\v -> Just $ case v of
"superscript" -> SupScrpt
"subscript" -> SubScrpt
_ -> BaseLn
, rUnderline =
findChild (elemName ns "w" "u") rPr >>=
findAttr (elemName ns "w" "val")