steppingstone: see oce-issues for tests

NAMESPACE

@@ -158,6 +158,7 @@ export(
     handleFlags,
     handleFlagsInternal,
     imagep,
+    inferUnits,
     initializeFlagScheme,
     initializeFlagSchemeInternal,
     initializeFlags,

R/units.R

@@ -226,3 +226,78 @@ as.unit <- function(u, default = list(unit = expression(), scale = "")) {
         }
     }
 }
+
+#' Infer units and scales from character strings
+#'
+#' @param s vector of character values.
+#'
+#' @param dictionary either a data frame or a string indicating a csv
+#' file that holds a data frame.  If a string, and if it ends in `".csv"`,
+#' then that file is used, but if it has another ending, it is taken
+#' as an indicator of a built-in file that is provided with
+#' the package, named `units_`, followed by the supplied `dictionary`
+#' value, and ending with `.csv`.
+#'
+#' @param ignore.case logical alue indicating whether to ignore the
+#' case in `strings`.  This defaults to TRUE, so that e.g. `"deg C"`
+#' and `"deg c"` can both be matched easily.
+#'
+#' @return if the unit is recognized, a list is returned, with the first
+#' column, named `unit`, being an [expression()] and the second,
+#' named `scale`, being an optional descriptor of the unit.
+#'
+#' @author Dan Kelley
+inferUnits <- function(strings, dictionary = "default", ignore.case = TRUE, debug = 0) {
+    oceDebug(debug, "inferUnits(..., dictionary=",
+             if (is.data.frame(dictionary)) {
+                 "[data frame]"
+             } else if (is.character(dictionary)) {
+                 paste0("\"", dictionary, "\"")
+             },
+             ") START\n", sep = "", unindent = 1)
+    if (is.character(dictionary)) {
+        if (!grepl(".csv$", dictionary)) {
+            dictionary <- system.file("extdata", paste0("units_", dictionary, ".csv"), package = "oce")
+            oceDebug(debug, "using internal dictionary \"", dictionary, "\"\n")
+        }
+        dictionary <- read.csv(dictionary, header = FALSE)
+    }
+    if (!is.data.frame(dictionary)) {
+        stop("dictionary must be either a data frame or a character string")
+    }
+    message("DAN 1")
+    dictionary <- cbind(dictionary, data.frame(V4 = paste0("^", dictionary$V1, "$")))
+    message("DAN 2")
+    dictionary$V4 <- gsub("#", "[0-9]", dictionary$V4)
+    message("DAN 3")
+    stringsOrig <- strings
+    if (ignore.case) {
+        strings <- tolower(strings)
+    }
+    n <- length(strings)
+    message("DAN 4")
+    rval <- vector("list", n)
+    for (i in seq_len(n)) {
+        message("DAN 5 i=", i, " string=\"", strings[i], "\"")
+        w <- which(sapply(dictionary$V4, \(p) grepl(p, strings[i])))
+        message("DAN 6 i=", i)
+        wlen <- length(w)
+        message("DAN 7 wlen=", wlen)
+        if (wlen > 1L) {
+            warning("unit matches more than 1 entry in the dictionary. Indices are: ", paste(w, collapse=" "))
+            print(dictionary[w, ])
+            w <- w[1]
+        }
+        if (length(w) == 1) {
+            #if (i == 9) browser("DANNN")
+            rval[[i]] <- list(
+                unit = as.expression(parse(text = dictionary$V2[w])),
+                scale = dictionary$V3[w]
+            )
+        } else {
+            rval[[i]] <- list(unit = "unit?", scale = "scale?")
+        }
+    }
+    names(rval) <- stringsOrig
+    rval
+}

inst/extdata/units_default.csv

@@ -0,0 +1,106 @@
+"MicroEinstein[s]{0,1} m-2 s-1",mu*Einsten/m^2/s,
+"count[s]{0,1}",count,
+"dbar[s]{0,1}",dbar,
+"decibar[s]{0,1}",dbar,
+"degree[s]{0,1} decimal minute[s]{0,1}", degreeDecimalMinute,
+"degree[s]{0,1}",degree,
+"degree[s]{0,1}.C",degree*C,
+"degree[s]{0,1}.celsius",degree*C,
+"degree[s]{0,1}.east",degree*E,
+"degree[s]{0,1}.north",degree*N,
+"degree[s]{0,1}.south",degree*S,
+"degree[s]{0,1}.west",degree*W,
+"degree[s]{0,1}_C",degree*C,
+"degree[s]{0,1}_east",degree*East,
+"degree[s]{0,1}_north",degree*North,
+"pH unit[s]{0,1}",pH,
+%,percent,
+,,
+/m/sr,m^-1*sr^-1,
+1,,
+1/m,1/m,
+NTU,NTU,
+PSS-78,PSS-78,
+PSU,,PSS-78
+S m-1,S/m,
+S m\^-1,S/m,
+S/m,S/m
+W kg-1,W/kg
+W kg\^-1,W/kg
+W/kg,W/kg
+ah,A*hr,
+amp,A,
+amp-hrs,A*hr,
+bar,bar,
+bool,,
+boolean,,
+byte,,
+cc,cm^3,
+celsius,degree*C,
+db,dbar,
+dbar,dbar,
+deg,degree,
+degc,degree*C,
+deg C,degree*C,
+enum,,,
+inHg,inch*Hg,
+inch,inch,
+ipts[ -]68,degree*C,IPTS-68
+its[ -]90,degree*C,ITS-90
+.*[kK]g m-3,kg/m^3,
+.*[kK]g m^-3,kg/m^3,
+.*[kK]g/m\^3,kg/m^3,
+m s-1,m/s,
+m s\^-2,m/s^2
+m,m,
+m-1,1/m,
+m/s,m/s,
+m/s\^2,m/s^2
+mS cm-1,mS/cm,
+mS cm\^-1,mS/cm,
+mS/cm,mS/cm,
+mV,mV,
+mg m-3,mg/m^3,
+mg/m\^3,mg/m^3,
+micromol l-1,mu*mol/l,
+micromol l\^-1,mu*mol/l,
+micromol/l,mu*mol/l,
+micromole kg-1,mu*mol/kg,
+micromole kg\^-1,mu*mol/kg,
+micromole/kg,mu*mol/kg,
+ml [lL]-1,ml/l,
+ml [lL]\^-1,ml/l,
+ml/[lL],ml/l,
+muS cm-1,mu*S/cm,
+muS cm\^-1,mu*S/cm,
+muS/cm,mu*S/cm,
+nodim,,
+ppb,ppb,
+pss-78,,PSS-78
+psu,,PSS-78
+rad,rad,
+s m-1,s/m,
+s m\^-1,s/m,
+s,s,
+s/m,s/m,
+sec,s,
+seconds since 1970-01-01T00:00:00Z,s,since 1970-01-01
+seconds since 1990-01-01,s,since 1990-01-01
+uEinsteins s-1 m-2,mu*Einstein/m^2/s^1,
+uEinsteins s\^-1 m\^-2,mu*Einstein/m^2/s^1,
+uEinsteins/s/m\^2,mu*Einstein/m^2/s^1,
+ug/kg,mu*g/kg,
+ug/l,mu*g/l,
+umol kg-1,mu*mol/kg,
+umol l-1,mu*mol/l,
+umol l\^-1,mu*mol/l,
+umol/kg,mu*mol/kg,
+umol/l,mu*mol/l,
+unixtimestamp,s,since 1970-01-01
+uw cm\^-2 nm\^-1,mu*W/cm^2/nm,
+uw/cm-2 nm-1,mu*W/cm^2/nm,
+uw/cm\^2/nm,mu*W/cm^2/nm,
+volt,V,
+volts,V,
+watt,W,
+watts,W,