distinguish in and ex authors (close #271)

gnames · Nov 6, 2024 · feb8b4a · feb8b4a
1 parent 05e573a
commit feb8b4a
Show file tree

Hide file tree

Showing 10 changed files with 4,397 additions and 4,314 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -2,6 +2,7 @@
 
 ## Unreleased
 
+- Fix [#271]: distinguish between `ex` and `in`.
 - Fix [#270]: missing verbatim authorship for names that look similar to
   combination uninomial in ICZN.
 - Fix [#268]: if botanical author looks like a combination uninomial,

diff --git a/ent/parsed/parsed.go b/ent/parsed/parsed.go
@@ -209,7 +209,11 @@ type AuthGroup struct {
 	// authors, that sometimes appear in scientific names after "ex"
 	// qualifier.
 	ExAuthors *Authors `json:"exAuthors,omitempty"`
-	// ExAuthors provided only if "with_details=true" A "special" group of
+	// InAuthors provided only if "with_details=true" A "special" group of
+	// authors, that sometimes appear in scientific names after "in"
+	// qualifier.
+	InAuthors *Authors `json:"inAuthors,omitempty"`
+	// EmendAuthors provided only if "with_details=true" A "special" group of
 	// authors, that sometimes appear in scientific names after "emend."
 	// qualifier.
 	EmendAuthors *Authors `json:"emendAuthors,omitempty"`

diff --git a/ent/parsed/warning.go b/ent/parsed/warning.go
@@ -17,7 +17,9 @@ const (
 	AuthEmendWarn
 	AuthEmendWithoutDotWarn
 	AuthExWarn
+	AuthInWarn
 	AuthExWithDotWarn
+	AuthInWithDotWarn
 	AuthMissingOneParensWarn
 	AuthQuestionWarn
 	AuthShortWarn
@@ -78,8 +80,10 @@ var warningMap = map[Warning]string{
 	AuthDoubleParensWarn:                  "Authorship in double parentheses",
 	AuthEmendWarn:                         "Emend authors are not required",
 	AuthEmendWithoutDotWarn:               "`emend` without a period",
-	AuthExWarn:                            "Ex authors are not required (ICZN only)",
+	AuthExWarn:                            "`ex` authors are not required (ICZN only)",
+	AuthInWarn:                            "`in` authors are not required",
 	AuthExWithDotWarn:                     "`ex` ends with a period",
+	AuthInWithDotWarn:                     "`in` ends with a period",
 	AuthMissingOneParensWarn:              "Authorship is missing one parenthesis",
 	AuthQuestionWarn:                      "Author as a question mark",
 	AuthShortWarn:                         "Author is too short",
@@ -150,7 +154,9 @@ var WarningQualityMap = map[Warning]int{
 	AuthEmendWarn:                         2,
 	AuthEmendWithoutDotWarn:               3,
 	AuthExWarn:                            2,
+	AuthInWarn:                            2,
 	AuthExWithDotWarn:                     3,
+	AuthInWithDotWarn:                     3,
 	AuthMissingOneParensWarn:              4,
 	AuthQuestionWarn:                      4,
 	AuthShortWarn:                         3,

diff --git a/ent/parsed/warning_test.go b/ent/parsed/warning_test.go
@@ -34,7 +34,7 @@ func TestJSONWarn(t *testing.T) {
 		{dataOb{"Tail", parsed.TailWarn, []int{}},
 			`{"f1":"Tail","warning":"Unparsed tail","f2":[]}`},
 		{dataOb{"AuthEx", parsed.AuthExWarn, []int{2, 3, 4}},
-			`{"f1":"AuthEx","warning":"Ex authors are not required (ICZN only)","f2":[2,3,4]}`},
+			`{"f1":"AuthEx","warning":"` + "`ex`" + ` authors are not required (ICZN only)","f2":[2,3,4]}`},
 	}
 	enc := gnfmt.GNjson{}
 	var dob dataOb

diff --git a/ent/parser/ast.go b/ent/parser/ast.go
@@ -980,6 +980,7 @@ type teamType int
 const (
 	teamDefault teamType = iota
 	teamEx
+	teamIn
 	teamEmend
 )
 
@@ -1020,6 +1021,15 @@ func (p *Engine) newAuthorsGroupNode(n *node32) *authorsGroupNode {
 			p.addWarn(parsed.AuthExWithDotWarn)
 		}
 		t2wrd.Normalized = "ex"
+	case ruleAuthorIn:
+		p.addWarn(parsed.AuthInWarn)
+		t2t = teamIn
+		t2wrd = p.newWordNode(n, parsed.AuthorWordType)
+		inWrd := strings.TrimSpace(t2wrd.Verbatim)
+		if inWrd[len(inWrd)-1] == '.' {
+			p.addWarn(parsed.AuthInWithDotWarn)
+		}
+		t2wrd.Normalized = "in"
 	case ruleAuthorEmend:
 		p.addWarn(parsed.AuthEmendWarn)
 		t2t = teamEmend

diff --git a/ent/parser/engine.go b/ent/parser/engine.go
@@ -187,6 +187,7 @@ var nodeRules = map[pegRule]struct{}{
 	ruleAuthorEmend:                     {},
 	ruleAuthorEtAl:                      {},
 	ruleAuthorEx:                        {},
+	ruleAuthorIn:                        {},
 	ruleAuthorPrefix:                    {},
 	ruleAuthorSep:                       {},
 	ruleAuthorSuffix:                    {},

diff --git a/ent/parser/grammar.peg b/ent/parser/grammar.peg
@@ -55,7 +55,7 @@ GenusWord <- (AbbrGenus / UninomialWord) !(_ AuthorWord)
 
 InfraspGroup <- InfraspEpithet (_ InfraspEpithet)?  (_ InfraspEpithet)?
 
-InfraspEpithet <- (Rank _?)? !(AuthorEx) Word (_ IgnoredWord)? (_? Authorship)?
+InfraspEpithet <- (Rank _?)? !(AuthorEx / AuthorIn) Word (_ IgnoredWord)? (_? Authorship)?
 
 CultivarWordGroup <-  ((RankCultivar _)? CultivarApostrophe
                       CultivarRecursive CultivarApostrophe) /
@@ -72,7 +72,7 @@ CultivarRecursive <- NotHybridChar CultivarRecursive / &CultivarApostrophe
 
 CultivarApostrophe <- '\'' / '‘' / '’' / '"' / '“' / '”'
 
-SpeciesEpithet <- !(AuthorEx) Word (_ IgnoredWord)? (_? Authorship)?
+SpeciesEpithet <- !(AuthorEx / AuthorIn) Word (_ IgnoredWord)? (_? Authorship)?
 
 IgnoredWord <- 'mihi.' / 'mihi'
 
@@ -206,7 +206,7 @@ BasionymAuthorship1 <- '(' _? AuthorsGroup _? ')'
 
 BasionymAuthorship2Parens <- '(' _? '(' _? AuthorsGroup _? ')' _? ')'
 
-AuthorsGroup <- AuthorsTeam (','?_ (AuthorEmend / AuthorEx) AuthorsTeam)?
+AuthorsGroup <- AuthorsTeam (','?_ (AuthorEmend / AuthorEx / AuthorIn) AuthorsTeam)?
 
 AuthorsTeam <- Author (AuthorSep Author)* (_? ','? _? Year)?
 
@@ -218,7 +218,9 @@ AuthorSep2 <- _? ',' _?
 
 AuthorSepSpanish <- _? 'y' _?
 
-AuthorEx <- ('ex' '.'? / 'ms' _ 'in' / 'in') _
+AuthorEx <- ('ex' '.'? ) _
+
+AuthorIn <- ( 'ms' _ 'in' / 'in') _
 
 AuthorEmend <- 'emend' '.'? _