update OSD parsing: effervescence, drop ordered factors

R/parseOSD_functions.R

@@ -94,7 +94,10 @@
   m <- tolower(m)
 
   # convert to ordered factor
-  m <- factor(m, levels = textures, ordered = TRUE)
+  #
+  # m <- factor(m, levels = textures, ordered = TRUE)
+  #
+  # factors cannot be preserved in JSON output, and wont work for multiple classes/ranges of classes
 
   return(m)
 }
@@ -196,33 +199,19 @@
   m <- tolower(m)
 
   # return as an ordered factor acidic -> basic
-  m <- factor(m, levels = pH_classes, ordered = TRUE)
+  # m <- factor(m, levels = pH_classes, ordered = TRUE)
+  # factors cannot be preserved in JSON output, and wont work for multiple classes/ranges of classes
 
   return(m)
 }
 
-
-
 # vectorized parsing of effervescence class
-#' @importFrom stringi stri_match
-.parse_eff_class <- function(text) {
-
-  # mineral texture classes
-  .classes <- c('noneffervescent', 'very slightly effervescent', 'slightly effervescent', 'strongly effervescent', 'violently effervescent')
-
-  ## 2019-05-29: generalized for all non-greedy, exact matching
-  m <- .findClass(needle = .classes, haystack = text)
-  m <- tolower(m)
-
-  # return as an ordered factor acidic -> basic
-  m <- factor(m, levels = .classes, ordered = TRUE)
-
-  return(m)
-
+.parse_eff_class <- function(x) {
+  .zerochar_to_na(gsub("^.*[;,]? ?\\b(very [a-z]+ effervescen[tce]+ (to|and|or) [a-z ]+ ?effervescen[tce]+).*$|^.*[;,]? ?\\b([a-z]+ ?effervescen[tce]+ (to|and|or) [a-z]+ ?effervescen[tce]+).*$|^.*[;,] ?\\b(very [a-z]+ effervescen[tce]+).*$|^.*[;,] ?\\b([a-z]+ ?effervescen[tce]+).*$|^.*[;,]? ?\\b(very [a-z]+ effervescen[tce]+).*$|^.*[;,]? ?\\b([a-z]+ ?effervescen[tce]+).*$|.*",
+                                           "\\1\\3\\5\\6\\7\\8", x, ignore.case = TRUE))
+  # factors cannot be preserved in JSON output, and wont work for multiple classes/ranges of classes
 }
 
-
-
 # vectorized parsing of drainage class
 #' @importFrom stringi stri_match
 .parse_drainage_class <- function(text) {
@@ -248,7 +237,6 @@
 
   # return as an ordered factor
   # m <- factor(m, levels = classes, ordered = TRUE)
-
   # factors cannot be preserved in JSON output, and wont work for multiple classes/ranges of classes
 
   return(m)
@@ -324,11 +312,11 @@
   #       "O" = "0"
   #       "l" = "1"
   ## ideas: http://stackoverflow.com/questions/15474741/python-regex-optional-capture-group
-  
-  ## TODO: it isn't clear if the new files will be in 
+
+  ## TODO: it isn't clear if the new files will be in
   # expect em dashes (\u2014) used after horizon designation as of May 2023
   # https://github.com/ncss-tech/SoilKnowledgeBase/issues/64
-  
+
   # detect horizons with both top and bottom depths
   hz.rule <-            "([\\^\\'\\/a-zA-Z0-9]+)\\s*[-=\u2014]+\\s*([Ol0-9.]+)\\s*?(to|-)?\\s+?([Ol0-9.]+)\\s*?(in|inches|cm|centimeters)"
 
@@ -494,7 +482,7 @@
   res$pH <- .parse_pH(narrative.data$narrative)
   res$pH_class <- .parse_pH_class(narrative.data$narrative)
   res$eff_class <- .parse_eff_class(narrative.data$narrative)
-  
+
   bdy <- .parse_hz_boundary(narrative.data$narrative)
   res$distinctness <- bdy$distinctness
   res$topography <- bdy$topography

inst/extdata/OSD/A/AAZDAHL.json

@@ -135,7 +135,7 @@
         "cf_class": "NA",
         "pH": "NA",
         "pH_class": "moderately alkaline",
-        "eff_class": "NA",
+        "eff_class": "violent effervescence",
         "distinctness": "gradual",
         "topography": "wavy",
         "narrative": "Bk--20 to 36 inches; grayish brown (2.5Y 5/2) clay loam; weak medium subangular blocky structure; friable; about 5 percent coarse fragments; violent effervescence; moderately alkaline; gradual wavy boundary.  (0 to 20 inches thick)"
@@ -158,7 +158,7 @@
         "cf_class": "NA",
         "pH": "NA",
         "pH_class": "moderately alkaline",
-        "eff_class": "NA",
+        "eff_class": "strong effervescence",
         "distinctness": "NA",
         "topography": "NA",
         "narrative": "C--36 to 60 inches; light olive brown (2.5Y 5/4) clay loam; common fine faint yellowish brown (10YR 5/6) and few fine prominent gray (5Y 5/1) mottles; massive; friable; about 5 percent coarse fragments; strong effervescence; moderately alkaline."

inst/extdata/OSD/A/ABERDEEN.json

@@ -181,7 +181,7 @@
         "cf_class": "NA",
         "pH": "NA",
         "pH_class": "slightly alkaline",
-        "eff_class": "NA",
+        "eff_class": "strong effervescence",
         "distinctness": "clear",
         "topography": "wavy",
         "narrative": "Bkyz1--26 to 31 inches; light gray (2.5Y 7/2) silty clay loam, grayish brown (2.5Y 5/2) moist; weak medium prismatic structure parting to weak medium subangular blocky; hard, firm, sticky and plastic; common fine nests of gypsum and other salts; common very fine accumulations of carbonate; strong effervescence; slightly alkaline; clear wavy boundary."
@@ -204,7 +204,7 @@
         "cf_class": "NA",
         "pH": "NA",
         "pH_class": "slightly alkaline",
-        "eff_class": "NA",
+        "eff_class": "strong effervescence",
         "distinctness": "gradual",
         "topography": "wavy",
         "narrative": "Bkyz2--31 to 38 inches; light brownish gray (2.5Y 6/2) silty clay loam, dark grayish brown (2.5Y 4/2) moist; weak medium prismatic structure parting to weak medium subangular blocky; hard, firm, sticky and plastic; common fine nests of gypsum and other salts; common very fine accumulations of carbonate; strong effervescence; slightly alkaline; gradual wavy boundary.  (Combined Bkyz horizons 0 to 20 inches thick)"
@@ -227,7 +227,7 @@
         "cf_class": "NA",
         "pH": "NA",
         "pH_class": "slightly alkaline",
-        "eff_class": "NA",
+        "eff_class": "slight effervescence",
         "distinctness": "gradual",
         "topography": "wavy",
         "narrative": "C1--38 to 51 inches; light gray (2.5Y 7/2) silt loam, grayish brown (2.5Y 5/2) moist; few fine prominent of yellowish brown (10YR 5/6) redoximorphic concentrations and few fine distinct gray (10YR 5/1) moist redoximorphic depletions; massive; hard, friable, slightly sticky and slightly plastic; few fine threads and nests of gypsum and other salts; slight effervescence; slightly alkaline; gradual wavy boundary."
@@ -250,7 +250,7 @@
         "cf_class": "NA",
         "pH": "NA",
         "pH_class": "slightly alkaline",
-        "eff_class": "NA",
+        "eff_class": "slight effervescence",
         "distinctness": "NA",
         "topography": "NA",
         "narrative": "C2--51 to 60 inches; pale yellow (2.5Y 7/4) silt loam, laminated with thin layers of silty clay and very fine sandy loam, light olive brown (2.5Y 5/4) moist; common fine prominent yellowish brown (10YR 5/6) and strong brown (7.5YR 5/6) redoximorphic concentrations, and gray (10YR 5/1) moist redoximorphic depletions; massive; laminations 1 to 3 mm thick; slightly hard, friable, slightly sticky and slightly plastic; slight effervescence; slightly alkaline."

inst/extdata/OSD/A/ACKETT.json

@@ -158,7 +158,7 @@
         "cf_class": "extremely cobbly",
         "pH": 8.4,
         "pH_class": "moderately alkaline",
-        "eff_class": "NA",
+        "eff_class": "violent effervescence",
         "distinctness": "abrupt",
         "topography": "smooth",
         "narrative": "2Btkq--15 to 20 cm; light gray (10YR 7/2) extremely cobbly clay, very pale brown (10YR 7/3) moist; massive; extremely hard, extremely firm, moderately sticky and moderately plastic; common distinct clay films on faces of peds and in pores; many continuous silica cemented laminations throughout; fractures are 0.6 cm wide and are 20 cm apart; few very fine roots in fractures; few very fine tubular pores; 70 percent cobbles, 10 percent gravel; violent effervescence; moderately alkaline (pH 8.4); abrupt smooth boundary.  (0 to 8 cm thick)"
@@ -181,7 +181,7 @@
         "cf_class": "very gravelly",
         "pH": 8.4,
         "pH_class": "moderately alkaline",
-        "eff_class": "NA",
+        "eff_class": "violent effervescence",
         "distinctness": "abrupt",
         "topography": "smooth",
         "narrative": "2Btk--20 to 36 cm; very pale brown (10YR 7/3) very gravelly clay loam, pale brown (10YR 6/3) moist; weak medium subangular blocky structure; hard, firm, moderately sticky and moderately plastic; few very fine and fine roots; few very fine tubular pores; common distinct clay films on faces of peds and in pores; 40 percent gravel size duripan fragments; violent effervescence (25 percent calcium carbonate); moderately alkaline (pH 8.4); abrupt smooth boundary.  (8 to 18 cm thick)"
@@ -204,7 +204,7 @@
         "cf_class": "NA",
         "pH": "NA",
         "pH_class": "NA",
-        "eff_class": "NA",
+        "eff_class": "violent effervescence",
         "distinctness": "abrupt",
         "topography": "smooth",
         "narrative": "2Bkqm--36 to 71 cm; white (10YR 8/1) fractured indurated duripan; very pale brown (10YR 7/3) moist; massive; many continuous silica cemented laminations throughout the duripan; fractures are 0.6 cm wide and are 50 cm apart; few very fine roots in fractures of the duripan; violent effervescence; abrupt smooth boundary.  (20 to 38 cm thick)"
@@ -227,7 +227,7 @@
         "cf_class": "extremely gravelly",
         "pH": 8.2,
         "pH_class": "moderately alkaline",
-        "eff_class": "NA",
+        "eff_class": "violent effervescence",
         "distinctness": "abrupt",
         "topography": "smooth",
         "narrative": "3Bkq--71 to 127 cm; multi-colored extremely gravelly sand; single grain; loose in places; 80 percent gravel; weak carbonate-silica cementation with carbonate pendants on undersides of gravel; violent effervescence; moderately alkaline (pH 8.2); abrupt smooth boundary.  (25 to 60 cm)"

inst/extdata/OSD/A/ADE.json

@@ -181,7 +181,7 @@
         "cf_class": "NA",
         "pH": "NA",
         "pH_class": "moderately alkaline",
-        "eff_class": "NA",
+        "eff_class": "strong effervescence",
         "distinctness": "NA",
         "topography": "NA",
         "narrative": "C--60 to 70 inches; brownish yellow (10YR 6/6) fine sand; single grain; loose; strong effervescence; moderately alkaline."

inst/extdata/OSD/A/AGAR.json

@@ -158,7 +158,7 @@
         "cf_class": "NA",
         "pH": "NA",
         "pH_class": "slightly alkaline",
-        "eff_class": "NA",
+        "eff_class": "strong effervescence",
         "distinctness": "clear",
         "topography": "wavy",
         "narrative": "Bk1--18 to 22 inches; grayish brown (10YR 5/2) silty clay loam, dark grayish brown (10YR 4/2) moist; weak coarse prismatic structure parting to moderate medium  and fine subangular blocky; hard, friable; few fine accumulations of carbonate; strong effervescence; slightly alkaline; clear wavy boundary."
@@ -181,7 +181,7 @@
         "cf_class": "NA",
         "pH": "NA",
         "pH_class": "moderately alkaline",
-        "eff_class": "NA",
+        "eff_class": "strong effervescence",
         "distinctness": "gradual",
         "topography": "wavy",
         "narrative": "Bk2--22 to 34 inches; light brownish gray (2.5Y 6/2) silty clay loam, dark grayish brown (2.5Y 4/2) moist; weak coarse prismatic structure parting to weak medium subangular blocky; hard, friable; common medium accumulations of carbonate; strong effervescence; moderately alkaline; gradual wavy boundary."
@@ -204,7 +204,7 @@
         "cf_class": "NA",
         "pH": "NA",
         "pH_class": "moderately alkaline",
-        "eff_class": "NA",
+        "eff_class": "strong effervescence",
         "distinctness": "gradual",
         "topography": "wavy",
         "narrative": "Bk3--34 to 40 inches; light brownish gray (2.5Y 6/2) silt loam, grayish brown (2.5Y 5/2) moist; weak medium subangular blocky structure; hard, friable; common medium accumulations of carbonate; strong effervescence; moderately alkaline; gradual wavy boundary. (Combined Bk horizon is 10 to 25 inches.)"
@@ -227,7 +227,7 @@
         "cf_class": "NA",
         "pH": "NA",
         "pH_class": "moderately alkaline",
-        "eff_class": "NA",
+        "eff_class": "strong effervescence",
         "distinctness": "NA",
         "topography": "NA",
         "narrative": "C3--40 to 61 inches; light brownish gray (2.5Y 6/2) silt loam, dark grayish brown (2.5Y 4/2) moist; massive; slightly hard, friable; few fine and medium accumulations of carbonate; strong effervescence; moderately alkaline."

inst/extdata/OSD/A/AGENCY.json

@@ -204,7 +204,7 @@
         "cf_class": "NA",
         "pH": "NA",
         "pH_class": "NA",
-        "eff_class": "NA",
+        "eff_class": "moderately effervescent",
         "distinctness": "NA",
         "topography": "NA",
         "narrative": "2Crkq--29 to 33 inches; paralithic tuff with silica and calcium carbonate coatings along fractures; moderately effervescent. ( 0 to 6 inches thick )"

inst/extdata/OSD/A/AGUACHIQUITA.json

@@ -135,7 +135,7 @@
         "cf_class": "very gravelly",
         "pH": 8.2,
         "pH_class": "moderately alkaline",
-        "eff_class": "strongly effervescent",
+        "eff_class": "noneffervescent to strongly effervescent",
         "distinctness": "clear",
         "topography": "wavy",
         "narrative": "Bkq--10 to 20 inches; pale brown (10YR 6/3) very gravelly coarse sandy loam, dark yellowish brown (10YR 4/4) moist; weak medium subangular blocky structure; slightly hard, very friable, nonsticky and nonplastic; common very fine, few fine and medium roots; few very fine and fine interstitial and tubular pores; 50 percent pebbles, 1 percent cobbles and 0.1 percent stones; common fine (1 to 2 millimeter) calcium carbonate and silica coats on bottoms of rock fragments; noneffervescent to strongly effervescent; moderately alkaline (pH 8.2); clear wavy boundary. (8 to 20 inches thick)"
@@ -158,7 +158,7 @@
         "cf_class": "NA",
         "pH": "NA",
         "pH_class": "NA",
-        "eff_class": "strongly effervescent",
+        "eff_class": "noneffervescent to strongly effervescent",
         "distinctness": "clear",
         "topography": "wavy",
         "narrative": "Bkqm1--20 to 31 inches; light brown (7.5YR 6/3) extremely weakly cemented duripan, brown (7.5YR 4/4) moist; massive; moderately hard, friable, brittle; few very fine and fine roots; few very fine and fine interstitial pores; 50 percent pebbles, 3 percent cobbles, and 1 percent stones; common fine (1 to 2 millimeter) calcium carbonate and silica coats on bottoms of rock fragments; noneffervescent to strongly effervescent; clear wavy boundary."
@@ -181,7 +181,7 @@
         "cf_class": "NA",
         "pH": "NA",
         "pH_class": "NA",
-        "eff_class": "strongly effervescent",
+        "eff_class": "noneffervescent to strongly effervescent",
         "distinctness": "abrupt",
         "topography": "wavy",
         "narrative": "Bkqm2--31 to 43 inches; light brown (7.5YR 6/3) very weakly cemented duripan, brown (7.5YR 4/4) moist; massive; hard, firm, brittle; few very fine and fine roots; few very fine and fine interstitial pores; 50 percent pebbles, 3 percent cobbles, and 1 percent stones; common fine (1 to 2 millimeter) calcium carbonate and silica coats on bottoms of rock fragments; noneffervescent to strongly effervescent; abrupt wavy boundary. (Combined thickness of the Bkqm horizons is 15 to 35 inches thick)"

inst/extdata/OSD/A/AGUILAR.json

@@ -135,7 +135,7 @@
         "cf_class": "NA",
         "pH": 8.8,
         "pH_class": "strongly alkaline",
-        "eff_class": "NA",
+        "eff_class": "slight effervescence",
         "distinctness": "clear",
         "topography": "smooth",
         "narrative": "Btn2--10 to 14 inches (25 to 36 cm); brown (10YR 5/3), silty clay, brown (10YR 4/3) moist; moderate coarse columnar structure parting to strong medium subangular blocks; extremely hard, very firm, very sticky and very plastic; few very fine and fine roots; common continuous distinct clay films on faces of peds; common fine salt threads; slight effervescence, 21 percent sodium absorption ratio; strongly alkaline (pH 8.8); clear smooth boundary.  (combined thickness of the Btn horizons is 8 to 14 inches)"
@@ -158,7 +158,7 @@
         "cf_class": "NA",
         "pH": 8.8,
         "pH_class": "strongly alkaline",
-        "eff_class": "NA",
+        "eff_class": "strong effervescence",
         "distinctness": "clear",
         "topography": "smooth",
         "narrative": "Btny--14 to 23 inches (36 to 58 cm); brown (10YR 5/3) clay, brown (10YR 4/3) moist; moderate medium columnar structure parting to strong medium angular blocks; extremely hard, very firm, very sticky and very plastic; few very fine roots; common continuous distinct clay films on faces of peds; common medium salt and gypsum threads; strong effervescence, 21 percent sodium absorption ratio; strongly alkaline (pH 8.8); clear smooth boundary.  (7 to 14 inches thick)"
@@ -181,7 +181,7 @@
         "cf_class": "NA",
         "pH": 8.6,
         "pH_class": "strongly alkaline",
-        "eff_class": "NA",
+        "eff_class": "violent effervescence",
         "distinctness": "clear",
         "topography": "smooth",
         "narrative": "Btkny--23 to 29 inches (58 to 74 cm); brown (10YR 5/3) clay loam, brown (10YR 4/3) moist; strong medium subangular blocky structure; extremely hard, very firm, moderately sticky and moderately plastic; few patchy distinct clay films on faces of peds; common coarse carbonate threads and common coarse salt and gypsum masses; violent effervescence, 22 percent sodium absorption ratio; strongly alkaline (pH 8.6); clear smooth boundary.  (2 to 10 inches thick)"
@@ -204,7 +204,7 @@
         "cf_class": "NA",
         "pH": 8.4,
         "pH_class": "moderately alkaline",
-        "eff_class": "NA",
+        "eff_class": "violent effervescence",
         "distinctness": "gradual",
         "topography": "smooth",
         "narrative": "Bkny--29 to 45 inches (74 to 114 cm); grayish brown (10YR 5/2) silty clay loam, brown (10YR 5/3) moist; 18 percent sand; moderate medium subangular blocky structure; very hard, firm, moderately sticky and moderately plastic; common medium salt and gypsum threads; common medium distinct carbonate threads; violent effervescence (3 percent calcium carbonate equivalent), 22 percent sodium absorption ratio; moderately alkaline (pH 8.4); gradual smooth boundary.  (10 to 20 inches thick)"
@@ -227,7 +227,7 @@
         "cf_class": "NA",
         "pH": 8.2,
         "pH_class": "moderately alkaline",
-        "eff_class": "NA",
+        "eff_class": "violent effervescence",
         "distinctness": "NA",
         "topography": "NA",
         "narrative": "Bny--45 to 65 inches (114 to 165 cm); grayish brown (10YR 5/2) silty clay loam, brown (10YR 5/3) moist; weak medium subangular blocky structure; very hard, firm, moderately sticky and moderately plastic; common medium salt and gypsum threads; common medium carbonate threads; violent effervescence (2 percent calcium carbonate equivalent); 21 percent sodium absorption ratio; moderately alkaline (pH 8.2)."