From 05f85e8463b5a1004a2c71678f1fa63a79914277 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Georges=20Dup=C3=A9ron?= Date: Thu, 18 May 2017 11:45:40 +0200 Subject: [PATCH] Changed BibTeX parser to recognize any sequence of words starting with a lower case letter as the "von"-like part of the author name --- scribble-lib/scriblib/bibtex.rkt | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/scribble-lib/scriblib/bibtex.rkt b/scribble-lib/scriblib/bibtex.rkt index 90138639..4aae40f4 100644 --- a/scribble-lib/scriblib/bibtex.rkt +++ b/scribble-lib/scriblib/bibtex.rkt @@ -225,8 +225,9 @@ (author-name (trim one) (trim two) #:suffix (trim suffix))] [(pregexp #px"^(.*),(.*)$" (list _ two one)) (author-name (string-trim one) (string-trim two))] - [(pregexp #px"^(.*) (von|de la|van der) (.*)$" (list _ one von-like two)) - (author-name (string-trim one) (string-append von-like " " (string-trim two)))] + [(pregexp #px"^(.*?)\\s+(\\p{Ll}[^\\s]*(\\s+\\p{Ll}[^\\s]*)*)\\s+(.*)$" (list _ one von-like _ two)) + (author-name (string-trim one) + (string-append (string-trim von-like) " " (string-trim two)))] [space-separated (match (regexp-split #px"\\s+" space-separated) [(list one) (org-author-name one)] @@ -380,6 +381,24 @@ (authors (author-name "James Jack" "van der Earl Jones"))) + (check + print-as-equal-string? + (parse-author "James Jack von de la Earl Jones") + (authors + (author-name "James Jack" "von de la Earl Jones"))) + + (check + print-as-equal-string? + (parse-author "James Jack di Earl Jones") + (authors + (author-name "James Jack" "di Earl Jones"))) + + (check + print-as-equal-string? + (parse-author "First fOn bER Last") + (authors + (author-name "First" "fOn bER Last"))) + (check print-as-equal-string? (parse-author "Deci, Edward L. and Robert J. Vallerand and Pelletier, Luc G. and Ryan, Jr, Richard M.")