diff --git a/CHANGELOG.md b/CHANGELOG.md --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,12 @@ # citeproc changelog +## 0.13.0.1 + + * Detect terminal punctuation hidden by closing quotes (#179, + Andrew Dunning). + + * Clarify building executable in the README (#177). + ## 0.13 * Add `citationResetPosition` field to `Citation`. [API change] diff --git a/README.md b/README.md --- a/README.md +++ b/README.md @@ -28,11 +28,6 @@ - it is more flexible, not being tied to pandoc's types. -Unlike pandoc-citeproc, this library does not provide an -executable. It will be used in pandoc itself to provide -integrated citation support and bibliography format conversion -(so the pandoc-citeproc filter will no longer be necessary). - [CSL]: https://docs.citationstyles.org/en/stable/specification.html ## How to use it @@ -93,13 +88,13 @@ ## The citeproc executable -If the package is compiled with the `executable` flag, an -executable `citeproc` will be built. `citeproc` reads -a JSON-encoded `Inputs` object from `stdin` (or from -a file if a filename is provided) and writes -a JSON-encoded `Result` object to `stdout`. (It does so using -`CslJson Text` as the underlying type.) This executable -can be used to add citation processing to non-Haskell projects. +If the package is compiled with the `executable` flag +(`cabal build -fexecutable`), a command-line program `citeproc` +will be built. `citeproc` reads a JSON-encoded `Inputs` object +from `stdin` (or from a file if a filename is provided) and +writes a JSON-encoded `Result` object to `stdout`. (It does so +using `CslJson Text` as the underlying type.) This executable can +be used to add citation processing to non-Haskell projects. `citeproc --help` will summarize usage information. See the [man page](man/citeproc.1.md) for more information. diff --git a/citeproc.cabal b/citeproc.cabal --- a/citeproc.cabal +++ b/citeproc.cabal @@ -1,6 +1,6 @@ cabal-version: 2.2 name: citeproc -version: 0.13 +version: 0.13.0.1 synopsis: Generates citations and bibliography from CSL styles. description: citeproc parses CSL style files and uses them to generate a list of formatted citations and bibliography diff --git a/src/Citeproc/Types.hs b/src/Citeproc/Types.hs --- a/src/Citeproc/Types.hs +++ b/src/Citeproc/Types.hs @@ -119,7 +119,9 @@ import qualified Data.CaseInsensitive as CI import Control.Monad (foldM, guard, mzero) import Control.Applicative ((<|>), optional) -import Data.Char (isLower, isDigit, isLetter, isSpace, isAlphaNum, isAscii) +import Data.Char (GeneralCategory(FinalQuote), + generalCategory, isLower, isDigit, + isLetter, isSpace, isAlphaNum, isAscii) import Data.Text (Text) import GHC.Generics (Generic) import qualified Data.Text as T @@ -1693,10 +1695,30 @@ where xText = toText x yText = toText y - xEnd = if T.null xText then '\xFFFD' else T.last xText - yStart = if T.null yText then '\xFFFD' else T.head yText + yStart = fromMaybe '\xFFFD' (firstChar yText) + -- see #179 + xEnd = + if yStart == '.' + then fromMaybe xLast (terminalCharBeforeQuote xText) + else xLast + xLast = fromMaybe '\xFFFD' (lastChar xText) xTrimmed = dropTextWhileEnd (== xEnd) x yTrimmed = dropTextWhile (== yStart) y + firstChar = fmap fst . T.uncons + lastChar = fmap snd . T.unsnoc + terminalCharBeforeQuote t = + let trimmed = T.dropWhileEnd isSpace t + in case T.unsnoc trimmed of + Just (_, q) | isQuoteLike q -> + lastChar (T.dropWhileEnd isTrailingCloser trimmed) + _ -> Nothing + isQuoteLike c = + c == '"' + || c == '\'' + || generalCategory c == FinalQuote + isTrailingCloser c = + isSpace c + || isQuoteLike c keepFirst = if yTrimmed == y -- see #49 then x : fixPunct (y : zs) else fixPunct $ x : yTrimmed : zs diff --git a/test/extra/issue_179.txt b/test/extra/issue_179.txt new file mode 100644 --- /dev/null +++ b/test/extra/issue_179.txt @@ -0,0 +1,84 @@ +>>===== MODE =====>> +citation +<<===== MODE =====<< + + +>>===== RESULT =====>> +Doe, ‘Ends with period inside quotes.’ +Doe, ‘Ends with question mark?’ +Doe, ‘Ends with an exclamation mark!’ +Doe, ‘Ends with period outside quotes’. +<<===== RESULT =====<< + + +>>===== CITATION-ITEMS =====>> +[ + [ + { + "id": "ITEM-1", + "suffix": ", 'Ends with period inside quotes.'" + } + ], + [ + { + "id": "ITEM-1", + "suffix": ", 'Ends with question mark?'" + } + ], + [ + { + "id": "ITEM-1", + "suffix": ", 'Ends with an exclamation mark!'" + } + ], + [ + { + "id": "ITEM-1", + "suffix": ", 'Ends with period outside quotes'." + } + ] +] +<<===== CITATION-ITEMS =====<< + + +>>===== CSL =====>> + +<<===== CSL =====<< + + +>>===== INPUT =====>> +[ + { + "author": [ + { + "family": "Doe", + "given": "John" + } + ], + "id": "ITEM-1", + "type": "book" + } +] +<<===== INPUT =====<< + + +>>===== VERSION =====>> +1.0 +<<===== VERSION =====<< diff --git a/test/extra/issue_179_enUS.txt b/test/extra/issue_179_enUS.txt new file mode 100644 --- /dev/null +++ b/test/extra/issue_179_enUS.txt @@ -0,0 +1,77 @@ +>>===== MODE =====>> +citation +<<===== MODE =====<< + + +>>===== RESULT =====>> +Doe, “Ends with period inside quotes.” +Doe, “Ends with question mark?” +Doe, “Ends with an exclamation mark!” +<<===== RESULT =====<< + + +>>===== CITATION-ITEMS =====>> +[ + [ + { + "id": "ITEM-1", + "suffix": ", \"Ends with period inside quotes.\"" + } + ], + [ + { + "id": "ITEM-1", + "suffix": ", \"Ends with question mark?\"" + } + ], + [ + { + "id": "ITEM-1", + "suffix": ", \"Ends with an exclamation mark!\"" + } + ] +] +<<===== CITATION-ITEMS =====<< + + +>>===== CSL =====>> + +<<===== CSL =====<< + + +>>===== INPUT =====>> +[ + { + "author": [ + { + "family": "Doe", + "given": "John" + } + ], + "id": "ITEM-1", + "type": "book" + } +] +<<===== INPUT =====<< + + +>>===== VERSION =====>> +1.0 +<<===== VERSION =====<< diff --git a/test/extra/issue_179_paren.txt b/test/extra/issue_179_paren.txt new file mode 100644 --- /dev/null +++ b/test/extra/issue_179_paren.txt @@ -0,0 +1,63 @@ +>>===== MODE =====>> +citation +<<===== MODE =====<< + + +>>===== RESULT =====>> +Doe, (E.D. Wisc.). +<<===== RESULT =====<< + + +>>===== CITATION-ITEMS =====>> +[ + [ + { + "id": "ITEM-1", + "suffix": ", (E.D. Wisc.)" + } + ] +] +<<===== CITATION-ITEMS =====<< + + +>>===== CSL =====>> + +<<===== CSL =====<< + + +>>===== INPUT =====>> +[ + { + "author": [ + { + "family": "Doe", + "given": "John" + } + ], + "id": "ITEM-1", + "type": "book" + } +] +<<===== INPUT =====<< + + +>>===== VERSION =====>> +1.0 +<<===== VERSION =====<<