From a36a56b8ac5fea612c1d0614d4e1cb14ffc3a21b Mon Sep 17 00:00:00 2001
From: Jesse Rosenthal <jrosenthal@jhu.edu>
Date: Sun, 6 Aug 2017 19:26:50 -0700
Subject: [PATCH] Docx reader: Avoid 0-level headers.
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.
---
src/Text/Pandoc/Readers/Docx/Parse.hs | 11 +++++------
1 file changed, 5 insertions(+), 6 deletions(-)
diff --git a/src/Text/Pandoc/Readers/Docx/Parse.hs b/src/Text/Pandoc/Readers/Docx/Parse.hs
index 24615ba94..05ce691a6 100644
--- a/src/Text/Pandoc/Readers/Docx/Parse.hs
+++ b/src/Text/Pandoc/Readers/Docx/Parse.hs
@@ -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]