diff options
author | John MacFarlane <jgm@berkeley.edu> | 2018-11-20 23:43:21 -0500 |
---|---|---|
committer | John MacFarlane <jgm@berkeley.edu> | 2018-11-20 23:43:21 -0500 |
commit | d333c283cc7149462491e97e95d3ccfaefab84c2 (patch) | |
tree | 694c50ae32258b4e1abae6a64bbfcd6ff3d5dd62 /src | |
parent | 2d265917b0e9efdd065349032befb96daa021503 (diff) | |
download | pandoc-d333c283cc7149462491e97e95d3ccfaefab84c2.tar.gz |
Docx writer: Fix bookmarks to headers with long titles.
Word has a 40 character limit for bookmark names. In
addition, bookmarks must begin with a letter. Since
pandoc's auto-generated identifiers may not respect
these constraints, some internal links did not work.
With this change, pandoc uses a bookmark name based
on the SHA1 hash of the identifier when the identifier
isn't a legal bookmark name.
Closes #5091.
Diffstat (limited to 'src')
-rw-r--r-- | src/Text/Pandoc/Writers/Docx.hs | 22 |
1 files changed, 18 insertions, 4 deletions
diff --git a/src/Text/Pandoc/Writers/Docx.hs b/src/Text/Pandoc/Writers/Docx.hs index a441aeec7..c2a160320 100644 --- a/src/Text/Pandoc/Writers/Docx.hs +++ b/src/Text/Pandoc/Writers/Docx.hs @@ -41,19 +41,21 @@ import Control.Monad.Reader import Control.Monad.State.Strict import qualified Data.ByteString as B import qualified Data.ByteString.Lazy as BL -import Data.Char (isSpace, ord, toLower) +import Data.Char (isSpace, ord, toLower, isLetter) import Data.List (intercalate, isPrefixOf, isSuffixOf) import qualified Data.Map as M import Data.Maybe (fromMaybe, isNothing, mapMaybe, maybeToList) import qualified Data.Set as Set import qualified Data.Text as T import Data.Time.Clock.POSIX +import Data.Digest.Pure.SHA (sha1, showDigest) import Skylighting import System.Random (randomR, StdGen, mkStdGen) import Text.Pandoc.BCP47 (getLang, renderLang) import Text.Pandoc.Class (PandocMonad, report, toLang) import qualified Text.Pandoc.Class as P import Data.Time +import Text.Pandoc.UTF8 (fromStringLazy) import Text.Pandoc.Definition import Text.Pandoc.Generic import Text.Pandoc.Highlighting (highlight) @@ -1268,7 +1270,8 @@ inlineToOpenXML' opts (Note bs) = do -- internal link: inlineToOpenXML' opts (Link _ txt ('#':xs,_)) = do contents <- withTextPropM (rStyleM "Hyperlink") $ inlinesToOpenXML opts txt - return [ mknode "w:hyperlink" [("w:anchor",xs)] contents ] + return + [ mknode "w:hyperlink" [("w:anchor", toBookmarkName xs)] contents ] -- external link: inlineToOpenXML' opts (Link _ txt (src,_)) = do contents <- withTextPropM (rStyleM "Hyperlink") $ inlinesToOpenXML opts txt @@ -1427,7 +1430,18 @@ wrapBookmark :: (PandocMonad m) => String -> [Element] -> WS m [Element] wrapBookmark [] contents = return contents wrapBookmark ident contents = do id' <- getUniqueId - let bookmarkStart = mknode "w:bookmarkStart" [("w:id", id') - ,("w:name",ident)] () + let bookmarkStart = mknode "w:bookmarkStart" + [("w:id", id') + ,("w:name", toBookmarkName ident)] () bookmarkEnd = mknode "w:bookmarkEnd" [("w:id", id')] () return $ bookmarkStart : contents ++ [bookmarkEnd] + +-- Word imposes a 40 character limit on bookmark names and requires +-- that they begin with a letter. So we just use a hash of the +-- identifer when otherwise we'd have an illegal bookmark name. +toBookmarkName :: String -> String +toBookmarkName s = + case s of + (c:_) | isLetter c + , length s <= 40 -> s + _ -> 'X' : drop 1 (showDigest (sha1 (fromStringLazy s))) |