fix delimiter problems; probably also closes #25

Author: agricolamz

DESCRIPTION

@@ -2,7 +2,7 @@ Package: lingglosses
 Type: Package
 Title: Interlinear Glossed Linguistic Examples and Abbreviation Lists Generation
 Version: 0.0.9
-Depends: R (>= 3.5.0)
+Depends: R (>= 4.1.0)
 Authors@R: person("George", "Moroz",
                   role = c("aut", "cre"),
                   email = "[email protected]",
@@ -19,6 +19,6 @@ LazyData: true
 URL: https://CRAN.R-project.org/package=phonfieldwork, https://agricolamz.github.io/lingglosses/
 BugReports: https://github.com/agricolamz/lingglosses/issues
 Imports: kableExtra, knitr, gt, rmarkdown, utils, htmltools, methods
-RoxygenNote: 7.3.2.9000
+RoxygenNote: 7.3.3
 Suggests: testthat (>= 3.0.0)
 Config/testthat/edition: 3

NEWS.md

@@ -1,3 +1,7 @@
+# lingglosses 0.0.10
+
+- fix delimeter problems; probably also closes #25
+
 # lingglosses 0.0.9
 
 - add `docx` compatibility

R/add_gloss.R

@@ -23,7 +23,8 @@ add_gloss <- function(glosses){
 # remove formatting --------------------------------------------------------
   glosses2add <- gsub("[_\\*]", "", glosses[glosses == toupper(glosses)])
   without_escape <- which(!(grepl("^\\{", glosses2add) &
-                               grepl("\\}$", glosses2add)))
+                              grepl("\\}$", glosses2add)|
+                              grepl("[-\\.=:\\)\\(!\\?<>\\~\\+\uFF3D\uFF3B]", glosses2add)))
   glosses2add <- glosses2add[without_escape]
 
 # add glosses to the list --------------------------------------------------
@@ -35,7 +36,9 @@ add_gloss <- function(glosses){
   }
 # add small caps -----------------------------------------------------------
   glosses <- ifelse(glosses == toupper(glosses) &
-                      !(grepl("^\\{", glosses) & grepl("\\}$", glosses)),
+                      !(grepl("^\\{", glosses) &
+                          grepl("\\}$", glosses) |
+                          grepl("[-\\.=:\\)\\(!\\?<>\\~\\+\uFF3D\uFF3B]", glosses)),
                     small_caps(glosses),
                     glosses)
   glosses <- gsub("[\\}\\{]", "", glosses)

R/gloss_example.R

@@ -158,22 +158,26 @@ gloss_example <- function(transliteration,
   }
 
 # add glosses to the document gloss list -----------------------------------
-  single_gl <- unlist(strsplit(glosses_by_word, "[-\\.=:\\)\\(!\\?<>\\~\\+\uFF3D\uFF3B]"))
-  starts_with_punctuation <- single_gl[1] == ""
-  single_gl <- gsub(pattern = "<", replacement = "&lt;", single_gl)
-  single_gl <- gsub(pattern = ">", replacement = "&gt;", single_gl)
-  single_gl <- lingglosses::add_gloss(single_gl)
-  if(starts_with_punctuation){single_gl <- c("", single_gl)}
+  glosses_by_word |>
+    strsplit("(?=[-\\.=:\\)\\(!\\?<>\\~\\+\uFF3D\uFF3B])", perl = TRUE) |>
+    lapply(FUN = function(i){
+      gsub(pattern = "<", replacement = "&lt;", x = i) |>
+        gsub(pattern = ">", replacement = "&gt;", x = _)
+      }) ->
+    single_gl
+
+  single_gl |>
+    lapply(function(i){
+      lingglosses::add_gloss(i)
+    })
 
 # get delimiters back ------------------------------------------------------
-  delimiters <- unlist(strsplit(glosses,
-"[^-:\\.= \\)\\(!\\?\u201E\u201C\u2019\u201D\u00BB\u00AB\u201F<>\\~\\+\uFF3B\uFF3D]"))
-  delimiters <- c(delimiters[delimiters != ""], "")
-  if(!starts_with_punctuation){single_gl <- c(single_gl, rep("", sum(delimiters == ">")))}
-  glosses <- paste0(single_gl, delimiters, collapse = "")
-  glosses <- gsub("<span style=", "<span_style=", glosses)
-  glosses <- unlist(strsplit(glosses, " "))
-  glosses <- gsub("<span_style=", "<span style=", glosses)
+
+  single_gl |>
+    lapply(function(i){
+      paste0(i, collapse = "")
+    }) ->
+    glosses
 
 # italic of the language line ----------------------------------------------
   if(isTRUE(italic_transliteration) & !drop_transliteration){