Bug fix, re-number match algorithms (#179)

  -  re-number match algorithms in online table to be identical to manuscript
  -  edit function extract_genus to make genus uppercase
  -  edit match algorithms to ensure genus names match equivalent columns in resources and submitted names; previously comparing canonical names from resources with genus from submitted name derivations. Changes to extract_genus function probably good enough, but this should be standardised anyway
   - replace APC-known with APC-synonyms
   - bug fix to avoid genus-level phrase names that begin with a "family name" from being added to the list of genera

R/APCalign-package.R

@@ -53,7 +53,7 @@ utils::globalVariables(
     "family",
     "fuzzy_match_genus",
     "fuzzy_match_genus_APNI",
-    "fuzzy_match_genus_known",
+    "fuzzy_match_genus_synonym",
     "genus",
     "genus_accepted",
     "known",

R/align_taxa.R

@@ -35,16 +35,16 @@
 #' - binomial: the first two words in `stripped_name2`, required for matches that ignore all other text in the original_name; improves phrase name matches.
 #' - genus: the first two words in `cleaned_name`; required for genus-rank matches and reprocessing of genus-rank names.
 #' - fuzzy_match_genus: fuzzy match of genus column to best match among APC-accepted names; required for fuzzy matches of genus-rank names.
-#' - fuzzy_match_genus_known: fuzzy match of genus column to best match among APC-known names, only considering different matches to those documented under APC-accepted genera; required for fuzzy matches of genus-rank names.
+#' - fuzzy_match_genus_synonym: fuzzy match of genus column to best match among APC-known names, only considering different matches to those documented under APC-accepted genera; required for fuzzy matches of genus-rank names.
 #' - fuzzy_match_genus_APNI: fuzzy match of genus column to best match among APNI names, only considering different matches to those documented under APC-accepted and APC-known genera; required for fuzzy matches of genus-rank names.
 #' - fuzzy_match_cleaned_APC: fuzzy match of stripped_name to APC-accepted names; created for yet-to-be-aligned names at the match step 07a in the function `match_taxa`.
-#' - fuzzy_match_cleaned_APC_known: fuzzy match of stripped_name to APC-known names; created for yet-to-be-aligned names at the match step 07b in the function `match_taxa`.
+#' - fuzzy_match_cleaned_APC_synonym: fuzzy match of stripped_name to APC-known names; created for yet-to-be-aligned names at the match step 07b in the function `match_taxa`.
 #' - fuzzy_match_cleaned_APC_imprecise: imprecise fuzzy match of stripped_name to APC-accepted names; created for yet-to-be-aligned names at the match step 10a in the function `match_taxa`.
-#' - fuzzy_match_cleaned_APC_known_imprecise: imprecise fuzzy match of stripped_name to APC-accepted names; created for yet-to-be-aligned names at the match step 10b in the function `match_taxa`.
+#' - fuzzy_match_cleaned_APC_synonym_imprecise: imprecise fuzzy match of stripped_name to APC-accepted names; created for yet-to-be-aligned names at the match step 10b in the function `match_taxa`.
 #' - fuzzy_match_binomial: fuzzy match of binomial column to best match among APC-accepted names; created for yet-to-be-aligned names at match step 15a in the function `match_taxa`.
-#' - fuzzy_match_binomial_APC_known: fuzzy match of binomial column to best match among APC-known names; created for yet-to-be-aligned names at match step 15a in the function `match_taxa`.
+#' - fuzzy_match_binomial_APC_synonym: fuzzy match of binomial column to best match among APC-known names; created for yet-to-be-aligned names at match step 15a in the function `match_taxa`.
 #' - fuzzy_match_trinomial: fuzzy match of trinomial column to best match among APC-accepted names; created for yet-to-be-aligned names at match step 16a in the function `match_taxa`.
-#' - fuzzy_match_trinomial_known: fuzzy match of trinomial column to best match among APC-known names; created for yet-to-be-aligned names at match step 16b in the function `match_taxa`.
+#' - fuzzy_match_trinomial_synonym: fuzzy match of trinomial column to best match among APC-known names; created for yet-to-be-aligned names at match step 16b in the function `match_taxa`.
 #' - fuzzy_match_cleaned_APNI: fuzzy match of stripped_name to APNI names; created for yet-to-be-aligned names at the match step 16a in the function `match_taxa`.
 #' - fuzzy_match_cleaned_APNI_imprecise: imprecise fuzzy match of stripped_name to APNI names; created for yet-to-be-aligned names at the match step 17a in the function `match_taxa`.
 #' 
@@ -127,17 +127,17 @@ align_taxa <- function(original_name,
         aligned_name = NA_character_,
         aligned_reason = NA_character_,
         fuzzy_match_genus = NA_character_,
-        fuzzy_match_genus_known = NA_character_,
+        fuzzy_match_genus_synonym = NA_character_,
         fuzzy_match_genus_APNI = NA_character_,
         fuzzy_match_binomial = NA_character_,
-        fuzzy_match_binomial_APC_known = NA_character_,
+        fuzzy_match_binomial_APC_synonym = NA_character_,
         fuzzy_match_trinomial = NA_character_,
-        fuzzy_match_trinomial_known = NA_character_,
+        fuzzy_match_trinomial_synonym = NA_character_,
         fuzzy_match_cleaned_APC = NA_character_,
-        fuzzy_match_cleaned_APC_known = NA_character_,
+        fuzzy_match_cleaned_APC_synonym = NA_character_,
         fuzzy_match_cleaned_APNI = NA_character_,
         fuzzy_match_cleaned_APC_imprecise = NA_character_,
-        fuzzy_match_cleaned_APC_known_imprecise = NA_character_,
+        fuzzy_match_cleaned_APC_synonym_imprecise = NA_character_,
         fuzzy_match_cleaned_APNI_imprecise = NA_character_,
         taxonomic_dataset = NA_character_,
         taxon_rank = NA_character_,

R/create_taxonomic_update_lookup.R

@@ -31,7 +31,7 @@
 #' - update_reason: the explanation of a specific taxon name update (from an aligned name to an accepted or suggested name).
 #' - subclass: the subclass of the accepted name.
 #' - taxon_distribution: the distribution of the accepted name; only filled in if an APC accepted_name is available.
-#' - scientific_name_authorship: the authorship information for the accepted (or known) name; available for both APC and APNI names.
+#' - scientific_name_authorship: the authorship information for the accepted (or synonymous) name; available for both APC and APNI names.
 #' - taxon_ID: the unique taxon concept identifier for the accepted_name; only filled in if an APC accepted_name is available.
 #' - taxon_ID_genus: an identifier for the genus; only filled in if an APC-accepted genus name is available.
 #' - scientific_name_ID: an identifier for the nomenclatural (not taxonomic) details of a scientific name; available for both APC and APNI names.

R/load_taxonomic_resources.R

@@ -195,9 +195,10 @@ load_taxonomic_resources <-
         genus
       ) %>%
       dplyr::filter(taxon_rank %in% c("genus"), taxonomic_status == "accepted") %>%
+      dplyr::filter(!stringr::str_detect(stringr::word(genus, 1), "aceae$")) %>%
       dplyr::mutate(taxonomic_dataset = "APC")
 
-    taxonomic_resources[["genera_known"]] <-
+    taxonomic_resources[["genera_synonym"]] <-
       taxonomic_resources$APC %>%
       dplyr::select(
         canonical_name,
@@ -213,6 +214,7 @@ load_taxonomic_resources <-
       ) %>%
       dplyr::filter(taxon_rank %in% c("genus")) %>%
       dplyr::filter(!canonical_name %in% taxonomic_resources$genera_accepted$canonical_name) %>%
+      dplyr::filter(!stringr::str_detect(stringr::word(genus, 1), "aceae$")) %>%
       dplyr::mutate(taxonomic_dataset = "APC") %>%
       dplyr::distinct(canonical_name, .keep_all = TRUE)
 
@@ -229,13 +231,14 @@ load_taxonomic_resources <-
       ) %>%
       dplyr::filter(taxon_rank %in% c("genus")) %>%
       dplyr::filter(!canonical_name %in% taxonomic_resources$APC$canonical_name) %>%
+      dplyr::filter(!stringr::str_detect(stringr::word(genus, 1), "aceae$")) %>%
       dplyr::mutate(taxonomic_dataset = "APNI") %>%
       dplyr::distinct(canonical_name, .keep_all = TRUE)
 
     taxonomic_resources[["genera_all"]] <-
       dplyr::bind_rows(
         taxonomic_resources$genera_accepted,
-        taxonomic_resources$genera_known,
+        taxonomic_resources$genera_synonym,
         taxonomic_resources$genera_APNI
       ) %>%
       dplyr::mutate(